Compare commits
1 Commits
718e371eb5
..
main
| Author | SHA1 | Date | |
|---|---|---|---|
 ShiyuZhang
|
2897b32d0d |
@@ -0,0 +1,126 @@
|
||||
# Agent 网络流量快速实验工程
|
||||
|
||||
本工程用于快速完成以下闭环：
|
||||
|
||||
1. 通过大模型生成任务行为画像（任务阶段、工具调用、拆分、消息大小、处理时间等）；
|
||||
2. 将行为画像扩展为结构化 Agent 事件日志；
|
||||
3. 从训练日志估计状态转移、持续时间、消息大小、超时和分支参数；
|
||||
4. 使用双层状态机、节点队列和离散事件调度进行仿真；
|
||||
5. 自动完成预测验证、基线对比、压力实验和重试放大实验；
|
||||
6. 输出 CSV、JSON 和 PNG 图表。
|
||||
|
||||
## 快速开始
|
||||
|
||||
当前环境已具备主要依赖，直接运行：
|
||||
|
||||
```powershell
|
||||
cd agent_traffic_experiments
|
||||
python run_pipeline.py
|
||||
```
|
||||
|
||||
默认使用 `local` 模式，不需要 API Key。结果写入 `outputs/latest/`。
|
||||
|
||||
## 使用大模型生成行为画像
|
||||
|
||||
本工程兼容 OpenAI 风格的 `/v1/chat/completions` 接口。先设置环境变量：
|
||||
|
||||
```powershell
|
||||
$env:OPENAI_API_KEY="你的密钥"
|
||||
$env:OPENAI_BASE_URL="https://api.openai.com/v1"
|
||||
$env:OPENAI_MODEL="你要使用的模型名称"
|
||||
python run_pipeline.py --generator llm
|
||||
```
|
||||
|
||||
也可以使用其他兼容服务，只需修改 `OPENAI_BASE_URL` 和 `OPENAI_MODEL`。
|
||||
|
||||
大模型只负责生成少量、可解释的任务行为画像；本地生成器会校验画像并扩展成大量事件。这样比让大模型直接输出数万行日志更稳定、更便宜，也能保证消息 ID、父子关系、时间戳和流量统计一致。
|
||||
|
||||
如果 LLM 请求失败，程序默认自动回退到本地画像。使用 `--no-fallback` 可禁止回退。
|
||||
|
||||
## 常用命令
|
||||
|
||||
只生成数据：
|
||||
|
||||
```powershell
|
||||
python run_pipeline.py --steps generate
|
||||
```
|
||||
|
||||
生成数据、估参并运行实验：
|
||||
|
||||
```powershell
|
||||
python run_pipeline.py --steps generate,estimate,experiment
|
||||
```
|
||||
|
||||
使用已有数据重新实验：
|
||||
|
||||
```powershell
|
||||
python run_pipeline.py --steps estimate,experiment
|
||||
```
|
||||
|
||||
指定配置和输出目录：
|
||||
|
||||
```powershell
|
||||
python run_pipeline.py --config configs/default.yaml --output outputs/run_001
|
||||
```
|
||||
|
||||
## 输出说明
|
||||
|
||||
```text
|
||||
outputs/latest/
|
||||
data/
|
||||
behavior_profiles.json # LLM或本地生成的任务画像
|
||||
train_events.csv # 参数估计数据
|
||||
test_events.csv # 留出验证数据
|
||||
task_truth.csv # 测试任务真实聚合值
|
||||
parameters/
|
||||
estimated_parameters.json # 从训练日志估计的模型参数
|
||||
results/
|
||||
validation_metrics.csv # 完整模型与基线误差
|
||||
validation_predictions.csv # 逐场景预测值和真实值
|
||||
stress_results.csv # 到达率压力实验
|
||||
retry_results.csv # 超时与重试放大实验
|
||||
summary.json # 实验摘要
|
||||
figures/
|
||||
prediction_vs_truth.png
|
||||
model_comparison.png
|
||||
stress_curves.png
|
||||
retry_heatmap.png
|
||||
```
|
||||
|
||||
## 实验内容
|
||||
|
||||
### E1 预测验证
|
||||
|
||||
训练集用于估计参数，测试集作为“模拟实测值”。完整状态机模型预测测试场景的内部字节数、任务时延、消息数和工具调用数。
|
||||
|
||||
### E2 基线对比
|
||||
|
||||
- `static_mean`：固定平均流量放大倍数；
|
||||
- `no_context`：不区分任务类型和任务阶段；
|
||||
- `full_model`：按任务画像和估计参数运行状态机仿真。
|
||||
|
||||
### E3 压力实验
|
||||
|
||||
逐渐提高外部到达率，观察吞吐量、平均/P95延迟、队列峰值、失败率和流量放大系数。
|
||||
|
||||
### E4 重试放大实验
|
||||
|
||||
改变超时概率和最大重试次数，观察任务成功率、平均重试数和内部流量放大系数。
|
||||
|
||||
## 数据字段
|
||||
|
||||
事件日志主要字段包括：
|
||||
|
||||
- `timestamp`、`task_id`、`message_id`、`parent_message_id`；
|
||||
- `task_type`、`task_phase`、`source`、`destination`；
|
||||
- `state_before`、`state_after`、`state_duration_ms`；
|
||||
- `message_type`、`message_size_bytes`；
|
||||
- `queue_length`、`success`、`retry_count`、`is_external`。
|
||||
|
||||
## 注意事项
|
||||
|
||||
- 当前数据是用于方法验证的模拟数据，不能冒充真实生产日志；
|
||||
- LLM 画像应在报告中标注模型名称、生成时间和提示词版本；
|
||||
- 正式参赛前，应尽量用少量真实 Agent 日志替换或校准模拟参数；
|
||||
- 所有随机实验都由配置中的随机种子控制，便于复现。
|
||||
|
||||
Binary file not shown.
@@ -0,0 +1,37 @@
|
||||
seed: 20260813
|
||||
|
||||
generation:
|
||||
train_tasks_per_type: 260
|
||||
test_tasks_per_type: 100
|
||||
task_types:
|
||||
- simple_qa
|
||||
- tool_research
|
||||
- collaborative_analysis
|
||||
llm:
|
||||
temperature: 0.5
|
||||
timeout_seconds: 90
|
||||
max_tokens: 3500
|
||||
|
||||
network:
|
||||
agent_count: 8
|
||||
tool_count: 3
|
||||
coordinator: agent_0
|
||||
default_link_bandwidth_mbps: 20
|
||||
default_link_delay_ms: 8
|
||||
max_concurrency: 4
|
||||
queue_capacity: 500
|
||||
|
||||
simulation:
|
||||
replications: 16
|
||||
timeout_ms: 2200
|
||||
max_retries: 2
|
||||
retry_backoff_ms: 180
|
||||
|
||||
experiments:
|
||||
validation_tasks_per_scenario: 120
|
||||
arrival_rates_per_second: [0.5, 1, 2, 4, 6, 8, 10, 12]
|
||||
stress_duration_seconds: 180
|
||||
stress_warmup_seconds: 20
|
||||
timeout_probabilities: [0.0, 0.03, 0.08, 0.15, 0.25]
|
||||
retry_limits: [0, 1, 2, 3, 5]
|
||||
|
||||
@@ -0,0 +1,37 @@
|
||||
seed: 20260813
|
||||
|
||||
generation:
|
||||
train_tasks_per_type: 260
|
||||
test_tasks_per_type: 100
|
||||
task_types:
|
||||
- simple_qa
|
||||
- tool_research
|
||||
- collaborative_analysis
|
||||
llm:
|
||||
temperature: 0.5
|
||||
timeout_seconds: 90
|
||||
max_tokens: 3500
|
||||
|
||||
network:
|
||||
agent_count: 8
|
||||
tool_count: 3
|
||||
coordinator: agent_0
|
||||
default_link_bandwidth_mbps: 20
|
||||
default_link_delay_ms: 8
|
||||
max_concurrency: 4
|
||||
queue_capacity: 500
|
||||
|
||||
simulation:
|
||||
replications: 16
|
||||
timeout_ms: 2200
|
||||
max_retries: 2
|
||||
retry_backoff_ms: 180
|
||||
|
||||
experiments:
|
||||
validation_tasks_per_scenario: 120
|
||||
arrival_rates_per_second: [0.5, 1, 2, 4, 6, 8, 10, 12]
|
||||
stress_duration_seconds: 180
|
||||
stress_warmup_seconds: 20
|
||||
timeout_probabilities: [0.0, 0.03, 0.08, 0.15, 0.25]
|
||||
retry_limits: [0, 1, 2, 3, 5]
|
||||
|
||||
@@ -0,0 +1,52 @@
|
||||
{
|
||||
"metadata": {
|
||||
"generator": "local_builtin"
|
||||
},
|
||||
"profiles": [
|
||||
{
|
||||
"task_type": "simple_qa",
|
||||
"description": "单节点即可完成的简短问答，少量情况下调用工具。",
|
||||
"phase": "answering",
|
||||
"tool_probability": 0.1,
|
||||
"split_probability": 0.05,
|
||||
"mean_subtasks": 1.2,
|
||||
"timeout_probability": 0.02,
|
||||
"failure_probability": 0.01,
|
||||
"think_time_ms_mean": 420.0,
|
||||
"think_time_cv": 0.55,
|
||||
"request_size_bytes_mean": 1800.0,
|
||||
"response_size_bytes_mean": 2600.0,
|
||||
"message_size_cv": 0.45
|
||||
},
|
||||
{
|
||||
"task_type": "tool_research",
|
||||
"description": "需要搜索、数据库或工具结果的研究任务。",
|
||||
"phase": "evidence_collection",
|
||||
"tool_probability": 0.78,
|
||||
"split_probability": 0.2,
|
||||
"mean_subtasks": 1.8,
|
||||
"timeout_probability": 0.07,
|
||||
"failure_probability": 0.025,
|
||||
"think_time_ms_mean": 900.0,
|
||||
"think_time_cv": 0.75,
|
||||
"request_size_bytes_mean": 3200.0,
|
||||
"response_size_bytes_mean": 8500.0,
|
||||
"message_size_cv": 0.7
|
||||
},
|
||||
{
|
||||
"task_type": "collaborative_analysis",
|
||||
"description": "协调多个执行 Agent 并汇总结果的复杂分析任务。",
|
||||
"phase": "multi_agent_synthesis",
|
||||
"tool_probability": 0.48,
|
||||
"split_probability": 0.82,
|
||||
"mean_subtasks": 3.4,
|
||||
"timeout_probability": 0.09,
|
||||
"failure_probability": 0.035,
|
||||
"think_time_ms_mean": 1450.0,
|
||||
"think_time_cv": 0.85,
|
||||
"request_size_bytes_mean": 5200.0,
|
||||
"response_size_bytes_mean": 11800.0,
|
||||
"message_size_cv": 0.8
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -0,0 +1,301 @@
|
||||
task_id,task_type,task_phase,latency_ms,internal_bytes,input_bytes,amplification,message_count,tool_calls,retries,success
|
||||
collaborative_analysis_00000,collaborative_analysis,multi_agent_synthesis,6111.839000000004,62448,1205,51.824066390041494,7,1,0,True
|
||||
collaborative_analysis_00001,collaborative_analysis,multi_agent_synthesis,7858.875999999981,57236,2452,23.34257748776509,7,0,0,True
|
||||
collaborative_analysis_00002,collaborative_analysis,multi_agent_synthesis,3745.010999999977,36184,6916,5.231925968768074,5,1,0,True
|
||||
collaborative_analysis_00003,collaborative_analysis,multi_agent_synthesis,3370.6700000000183,15600,1146,13.612565445026178,3,0,0,True
|
||||
collaborative_analysis_00004,collaborative_analysis,multi_agent_synthesis,3970.753000000002,26927,5695,4.728182616330114,5,1,0,True
|
||||
collaborative_analysis_00005,collaborative_analysis,multi_agent_synthesis,3692.181000000005,9783,2845,3.438664323374341,3,0,0,True
|
||||
collaborative_analysis_00006,collaborative_analysis,multi_agent_synthesis,12027.614,101344,5088,19.91823899371069,9,1,0,True
|
||||
collaborative_analysis_00007,collaborative_analysis,multi_agent_synthesis,3174.7689999999975,13427,10177,1.3193475483934363,3,0,0,True
|
||||
collaborative_analysis_00008,collaborative_analysis,multi_agent_synthesis,4553.435000000008,106516,5924,17.98041863605672,13,2,0,True
|
||||
collaborative_analysis_00009,collaborative_analysis,multi_agent_synthesis,20393.187000000013,136393,8870,15.376888387824126,19,3,0,True
|
||||
collaborative_analysis_00010,collaborative_analysis,multi_agent_synthesis,9716.779000000002,43830,1420,30.866197183098592,9,2,0,True
|
||||
collaborative_analysis_00011,collaborative_analysis,multi_agent_synthesis,13658.126999999979,113877,6803,16.73923269145965,13,2,0,True
|
||||
collaborative_analysis_00012,collaborative_analysis,multi_agent_synthesis,5092.640999999986,138420,4391,31.523570940560237,13,2,0,True
|
||||
collaborative_analysis_00013,collaborative_analysis,multi_agent_synthesis,2393.601999999987,13198,8494,1.5538026842477042,3,0,0,True
|
||||
collaborative_analysis_00014,collaborative_analysis,multi_agent_synthesis,7330.83400000001,65750,876,75.05707762557077,11,2,0,True
|
||||
collaborative_analysis_00015,collaborative_analysis,multi_agent_synthesis,16492.502,180400,2157,83.63467779323133,23,3,0,True
|
||||
collaborative_analysis_00016,collaborative_analysis,multi_agent_synthesis,16875.831000000006,205302,2605,78.81074856046065,19,3,0,True
|
||||
collaborative_analysis_00017,collaborative_analysis,multi_agent_synthesis,9850.209000000006,147782,1988,74.33702213279678,19,3,0,True
|
||||
collaborative_analysis_00018,collaborative_analysis,multi_agent_synthesis,10007.738999999987,126126,4218,29.90184921763869,15,2,0,True
|
||||
collaborative_analysis_00019,collaborative_analysis,multi_agent_synthesis,11525.198999999986,106483,1192,89.33137583892618,7,1,0,True
|
||||
collaborative_analysis_00020,collaborative_analysis,multi_agent_synthesis,5159.906000000006,59557,2210,26.94886877828054,9,2,0,True
|
||||
collaborative_analysis_00021,collaborative_analysis,multi_agent_synthesis,4791.642999999994,57467,18445,3.1155868799132556,5,0,0,True
|
||||
collaborative_analysis_00022,collaborative_analysis,multi_agent_synthesis,11351.583000000006,75128,3315,22.663046757164405,9,1,0,True
|
||||
collaborative_analysis_00023,collaborative_analysis,multi_agent_synthesis,8277.253999999999,39603,5217,7.591144335825187,5,1,0,True
|
||||
collaborative_analysis_00024,collaborative_analysis,multi_agent_synthesis,19919.341000000004,167247,1166,143.43653516295026,23,5,0,True
|
||||
collaborative_analysis_00025,collaborative_analysis,multi_agent_synthesis,9099.73500000001,69536,6843,10.161625018266841,11,1,0,True
|
||||
collaborative_analysis_00026,collaborative_analysis,multi_agent_synthesis,3098.5450000000014,55189,7507,7.351671773011856,11,2,0,True
|
||||
collaborative_analysis_00027,collaborative_analysis,multi_agent_synthesis,6933.150000000012,128239,5952,21.545530913978496,13,3,0,True
|
||||
collaborative_analysis_00028,collaborative_analysis,multi_agent_synthesis,14684.41899999999,164414,1446,113.70262793914246,18,5,1,True
|
||||
collaborative_analysis_00029,collaborative_analysis,multi_agent_synthesis,22606.593000000004,130445,2700,48.31296296296296,13,3,2,True
|
||||
collaborative_analysis_00030,collaborative_analysis,multi_agent_synthesis,7566.215999999997,53530,2840,18.848591549295776,7,0,0,True
|
||||
collaborative_analysis_00031,collaborative_analysis,multi_agent_synthesis,9549.07,182717,560,326.28035714285716,11,2,0,True
|
||||
collaborative_analysis_00032,collaborative_analysis,multi_agent_synthesis,16413.354,140512,4336,32.40590405904059,13,1,0,True
|
||||
collaborative_analysis_00033,collaborative_analysis,multi_agent_synthesis,3107.8390000000127,25062,1526,16.42332896461337,3,0,0,True
|
||||
collaborative_analysis_00034,collaborative_analysis,multi_agent_synthesis,2382.689999999997,37813,4410,8.57437641723356,5,1,0,True
|
||||
collaborative_analysis_00035,collaborative_analysis,multi_agent_synthesis,6573.08900000001,42752,1231,34.72948822095857,9,2,0,True
|
||||
collaborative_analysis_00036,collaborative_analysis,multi_agent_synthesis,14503.11400000001,179234,7724,23.20481615743138,23,6,1,True
|
||||
collaborative_analysis_00037,collaborative_analysis,multi_agent_synthesis,6998.415999999992,40737,4407,9.243703199455412,5,1,0,True
|
||||
collaborative_analysis_00038,collaborative_analysis,multi_agent_synthesis,9218.387000000006,76646,5615,13.650222617987533,12,3,1,True
|
||||
collaborative_analysis_00039,collaborative_analysis,multi_agent_synthesis,14171.648999999974,82798,3958,20.919151086407275,13,2,0,True
|
||||
collaborative_analysis_00040,collaborative_analysis,multi_agent_synthesis,16203.926999999992,192384,4272,45.03370786516854,19,2,0,True
|
||||
collaborative_analysis_00041,collaborative_analysis,multi_agent_synthesis,8077.832999999999,86864,14703,5.907909950350269,9,1,0,True
|
||||
collaborative_analysis_00042,collaborative_analysis,multi_agent_synthesis,11980.147000000017,175669,4129,42.545168321627514,17,2,0,True
|
||||
collaborative_analysis_00043,collaborative_analysis,multi_agent_synthesis,8383.41299999999,86553,4556,18.99758560140474,11,1,0,True
|
||||
collaborative_analysis_00044,collaborative_analysis,multi_agent_synthesis,3781.3569999999854,21537,2248,9.580516014234876,5,1,0,True
|
||||
collaborative_analysis_00045,collaborative_analysis,multi_agent_synthesis,2871.480999999989,29178,3997,7.299974981235927,5,1,0,True
|
||||
collaborative_analysis_00046,collaborative_analysis,multi_agent_synthesis,1987.737999999979,21361,8073,2.6459804285891244,3,0,0,True
|
||||
collaborative_analysis_00047,collaborative_analysis,multi_agent_synthesis,10075.866999999987,219312,9941,22.061362036012472,17,3,0,True
|
||||
collaborative_analysis_00048,collaborative_analysis,multi_agent_synthesis,6179.957999999999,70354,2470,28.4834008097166,5,1,0,True
|
||||
collaborative_analysis_00049,collaborative_analysis,multi_agent_synthesis,3145.8080000000164,28609,4669,6.127436281859071,3,0,0,True
|
||||
collaborative_analysis_00050,collaborative_analysis,multi_agent_synthesis,6249.4649999999865,28317,882,32.105442176870746,7,1,0,True
|
||||
collaborative_analysis_00051,collaborative_analysis,multi_agent_synthesis,11702.425000000005,187198,1275,146.82196078431372,17,2,0,True
|
||||
collaborative_analysis_00052,collaborative_analysis,multi_agent_synthesis,10426.145999999988,122179,1403,87.08410548823949,13,2,0,True
|
||||
collaborative_analysis_00053,collaborative_analysis,multi_agent_synthesis,3776.5890000000013,10701,3073,3.482264887731858,3,0,0,True
|
||||
collaborative_analysis_00054,collaborative_analysis,multi_agent_synthesis,6411.059999999992,122716,3644,33.6761800219539,13,3,0,True
|
||||
collaborative_analysis_00055,collaborative_analysis,multi_agent_synthesis,9190.782999999981,87827,8202,10.707998049256279,13,1,0,True
|
||||
collaborative_analysis_00056,collaborative_analysis,multi_agent_synthesis,26072.79299999999,196393,2732,71.88616398243046,22,5,1,True
|
||||
collaborative_analysis_00057,collaborative_analysis,multi_agent_synthesis,6656.256000000013,33081,7347,4.502654144548796,7,1,0,True
|
||||
collaborative_analysis_00058,collaborative_analysis,multi_agent_synthesis,5274.61199999999,58229,9303,6.259163710630979,8,2,1,True
|
||||
collaborative_analysis_00059,collaborative_analysis,multi_agent_synthesis,5612.335999999999,17516,7543,2.3221529895267135,3,0,0,True
|
||||
collaborative_analysis_00060,collaborative_analysis,multi_agent_synthesis,7323.184999999995,88159,6584,13.389884568651276,5,1,0,True
|
||||
collaborative_analysis_00061,collaborative_analysis,multi_agent_synthesis,13041.410999999982,39582,4651,8.510427864975274,5,0,0,True
|
||||
collaborative_analysis_00062,collaborative_analysis,multi_agent_synthesis,5737.938000000014,55676,4041,13.777777777777779,11,2,0,True
|
||||
collaborative_analysis_00063,collaborative_analysis,multi_agent_synthesis,13871.848999999998,111676,5758,19.39492879472039,18,5,1,True
|
||||
collaborative_analysis_00064,collaborative_analysis,multi_agent_synthesis,14159.884000000005,93620,743,126.00269179004037,11,2,0,True
|
||||
collaborative_analysis_00065,collaborative_analysis,multi_agent_synthesis,2143.2680000000064,44223,2414,18.319386909693456,5,0,0,True
|
||||
collaborative_analysis_00066,collaborative_analysis,multi_agent_synthesis,9103.234999999984,120161,2301,52.22120817036071,11,0,0,True
|
||||
collaborative_analysis_00067,collaborative_analysis,multi_agent_synthesis,7975.786999999997,51818,2211,23.43645409317051,9,2,0,True
|
||||
collaborative_analysis_00068,collaborative_analysis,multi_agent_synthesis,10306.556999999997,143550,1168,122.90239726027397,15,3,0,True
|
||||
collaborative_analysis_00069,collaborative_analysis,multi_agent_synthesis,10491.949999999975,88142,1034,85.24371373307544,13,3,0,True
|
||||
collaborative_analysis_00070,collaborative_analysis,multi_agent_synthesis,5671.043999999994,92836,4373,21.229361994054425,7,1,0,True
|
||||
collaborative_analysis_00071,collaborative_analysis,multi_agent_synthesis,2233.918000000017,35792,908,39.418502202643175,5,1,0,True
|
||||
collaborative_analysis_00072,collaborative_analysis,multi_agent_synthesis,2779.2799999999997,19132,1140,16.782456140350877,3,0,0,True
|
||||
collaborative_analysis_00073,collaborative_analysis,multi_agent_synthesis,5933.890999999989,53137,2409,22.057700290577003,7,1,0,True
|
||||
collaborative_analysis_00074,collaborative_analysis,multi_agent_synthesis,11494.603000000012,198018,8671,22.836812363049244,15,5,1,True
|
||||
collaborative_analysis_00075,collaborative_analysis,multi_agent_synthesis,3800.8010000000068,92249,1891,48.78318350079323,7,0,0,True
|
||||
collaborative_analysis_00076,collaborative_analysis,multi_agent_synthesis,15271.408000000009,110064,4836,22.759305210918114,13,4,2,True
|
||||
collaborative_analysis_00077,collaborative_analysis,multi_agent_synthesis,3524.1379999999936,49633,2359,21.03984739296312,7,0,0,True
|
||||
collaborative_analysis_00078,collaborative_analysis,multi_agent_synthesis,1085.5840000000114,34459,1481,23.267386900742743,3,0,0,True
|
||||
collaborative_analysis_00079,collaborative_analysis,multi_agent_synthesis,3396.9510000000014,7311,4899,1.492345376607471,3,0,0,True
|
||||
collaborative_analysis_00080,collaborative_analysis,multi_agent_synthesis,7375.2580000000025,40747,2612,15.599923430321592,10,3,1,True
|
||||
collaborative_analysis_00081,collaborative_analysis,multi_agent_synthesis,11392.599000000018,125175,5129,24.405342171963344,17,5,1,True
|
||||
collaborative_analysis_00082,collaborative_analysis,multi_agent_synthesis,4221.8009999999995,46903,1193,39.3151718357083,3,0,0,True
|
||||
collaborative_analysis_00083,collaborative_analysis,multi_agent_synthesis,4469.9559999999965,34392,7835,4.389534141671985,5,0,0,True
|
||||
collaborative_analysis_00084,collaborative_analysis,multi_agent_synthesis,14913.923000000012,148982,4218,35.32053105737316,17,5,2,False
|
||||
collaborative_analysis_00085,collaborative_analysis,multi_agent_synthesis,3174.0640000000158,26574,2863,9.281872162067762,3,0,0,True
|
||||
collaborative_analysis_00086,collaborative_analysis,multi_agent_synthesis,6104.687000000013,29578,2252,13.134103019538188,6,2,1,True
|
||||
collaborative_analysis_00087,collaborative_analysis,multi_agent_synthesis,3079.0619999999935,23392,7001,3.3412369661476933,3,0,0,True
|
||||
collaborative_analysis_00088,collaborative_analysis,multi_agent_synthesis,15710.582000000017,123812,1087,113.90248390064397,17,3,0,True
|
||||
collaborative_analysis_00089,collaborative_analysis,multi_agent_synthesis,9594.03499999999,123841,7467,16.585107807687155,15,3,0,True
|
||||
collaborative_analysis_00090,collaborative_analysis,multi_agent_synthesis,8018.177000000009,35223,2432,14.483141447368421,7,1,0,True
|
||||
collaborative_analysis_00091,collaborative_analysis,multi_agent_synthesis,8070.577999999983,85639,1800,47.577222222222225,9,1,0,True
|
||||
collaborative_analysis_00092,collaborative_analysis,multi_agent_synthesis,6954.7670000000035,30543,2606,11.720260936300845,8,2,1,True
|
||||
collaborative_analysis_00093,collaborative_analysis,multi_agent_synthesis,2334.4150000000072,9761,1259,7.75297855440826,3,0,0,True
|
||||
collaborative_analysis_00094,collaborative_analysis,multi_agent_synthesis,3988.2240000000024,53918,4052,13.306515301085884,7,0,0,True
|
||||
collaborative_analysis_00095,collaborative_analysis,multi_agent_synthesis,6538.421999999997,67526,4362,15.480513525905549,7,1,0,True
|
||||
collaborative_analysis_00096,collaborative_analysis,multi_agent_synthesis,7050.077000000016,89764,5545,16.188277727682596,9,0,0,True
|
||||
collaborative_analysis_00097,collaborative_analysis,multi_agent_synthesis,14613.135,138234,1905,72.56377952755905,18,4,1,True
|
||||
collaborative_analysis_00098,collaborative_analysis,multi_agent_synthesis,5859.162999999995,34186,15338,2.2288433954883295,6,2,1,True
|
||||
collaborative_analysis_00099,collaborative_analysis,multi_agent_synthesis,17759.783999999996,169187,11129,15.202354209722348,21,5,0,True
|
||||
simple_qa_00000,simple_qa,answering,855.1170000000001,3448,2896,1.1906077348066297,3,0,0,True
|
||||
simple_qa_00001,simple_qa,answering,1403.896,4962,1531,3.24101894186806,3,0,0,True
|
||||
simple_qa_00002,simple_qa,answering,1171.8220000000001,4350,787,5.527318932655654,3,0,0,True
|
||||
simple_qa_00003,simple_qa,answering,1504.4239999999998,2494,375,6.650666666666667,3,0,0,True
|
||||
simple_qa_00004,simple_qa,answering,1963.5280000000002,5963,591,10.089678510998308,5,1,0,True
|
||||
simple_qa_00005,simple_qa,answering,1452.445,5943,2101,2.8286530223703,3,0,0,True
|
||||
simple_qa_00006,simple_qa,answering,825.0729999999998,3757,1209,3.10752688172043,3,0,0,True
|
||||
simple_qa_00007,simple_qa,answering,926.895,3668,2132,1.7204502814258913,3,0,0,True
|
||||
simple_qa_00008,simple_qa,answering,1005.903,4694,1529,3.0699803793328972,3,0,0,True
|
||||
simple_qa_00009,simple_qa,answering,1038.875,5016,1632,3.073529411764706,3,0,0,True
|
||||
simple_qa_00010,simple_qa,answering,659.4789999999992,9518,859,11.080325960419092,3,0,0,True
|
||||
simple_qa_00011,simple_qa,answering,1125.273,3965,1038,3.8198458574181116,3,0,0,True
|
||||
simple_qa_00012,simple_qa,answering,1077.1380000000015,5386,1219,4.418375717801476,3,0,0,True
|
||||
simple_qa_00013,simple_qa,answering,1004.5659999999988,5660,889,6.366704161979753,3,0,0,True
|
||||
simple_qa_00014,simple_qa,answering,996.1830000000002,4420,1161,3.8070628768303187,3,0,0,True
|
||||
simple_qa_00015,simple_qa,answering,860.6720000000009,4252,1484,2.8652291105121295,3,0,0,True
|
||||
simple_qa_00016,simple_qa,answering,781.1749999999993,6704,1189,5.638351555929352,3,0,0,True
|
||||
simple_qa_00017,simple_qa,answering,700.6979999999992,4185,1526,2.7424639580602883,3,0,0,True
|
||||
simple_qa_00018,simple_qa,answering,1115.2699999999988,5439,1075,5.05953488372093,3,0,0,True
|
||||
simple_qa_00019,simple_qa,answering,850.3690000000006,3539,1636,2.16320293398533,3,0,0,True
|
||||
simple_qa_00020,simple_qa,answering,823.193999999999,5658,1063,5.322671683913453,3,0,0,True
|
||||
simple_qa_00021,simple_qa,answering,930.963000000002,6726,2009,3.3479342956694875,3,0,0,True
|
||||
simple_qa_00022,simple_qa,answering,742.083000000001,5048,1822,2.770581778265642,3,0,0,True
|
||||
simple_qa_00023,simple_qa,answering,1172.7469999999976,3674,1567,2.3446075303126994,3,0,0,True
|
||||
simple_qa_00024,simple_qa,answering,604.9790000000002,7257,1006,7.213717693836978,3,0,0,True
|
||||
simple_qa_00025,simple_qa,answering,1219.6170000000031,4464,2084,2.1420345489443378,3,0,0,True
|
||||
simple_qa_00026,simple_qa,answering,753.5990000000013,4068,1755,2.317948717948718,3,0,0,True
|
||||
simple_qa_00027,simple_qa,answering,791.2379999999998,5056,1373,3.6824471959213403,3,0,0,True
|
||||
simple_qa_00028,simple_qa,answering,827.5049999999986,3795,801,4.737827715355805,3,0,0,True
|
||||
simple_qa_00029,simple_qa,answering,677.6099999999979,4655,2300,2.023913043478261,3,0,0,True
|
||||
simple_qa_00030,simple_qa,answering,791.8140000000022,4267,720,5.926388888888889,3,0,0,True
|
||||
simple_qa_00031,simple_qa,answering,1215.0280000000002,7292,3124,2.3341869398207424,5,1,0,True
|
||||
simple_qa_00032,simple_qa,answering,1804.2910000000027,4607,2837,1.6238984843144166,3,0,0,True
|
||||
simple_qa_00033,simple_qa,answering,844.0370000000001,3221,1756,1.8342824601366743,3,0,0,True
|
||||
simple_qa_00034,simple_qa,answering,1057.2420000000022,5454,1504,3.6263297872340425,3,0,0,True
|
||||
simple_qa_00035,simple_qa,answering,1576.5220000000006,5750,1500,3.8333333333333335,3,0,0,True
|
||||
simple_qa_00036,simple_qa,answering,1026.4500000000005,7409,4583,1.616626663757364,3,0,0,True
|
||||
simple_qa_00037,simple_qa,answering,716.7670000000008,5122,1777,2.8823860438942037,3,0,0,True
|
||||
simple_qa_00038,simple_qa,answering,982.6349999999984,7826,1145,6.834934497816594,3,0,0,True
|
||||
simple_qa_00039,simple_qa,answering,701.6949999999973,5078,670,7.57910447761194,3,0,0,True
|
||||
simple_qa_00040,simple_qa,answering,1318.7110000000005,5824,2164,2.6913123844731976,3,0,0,True
|
||||
simple_qa_00041,simple_qa,answering,839.9459999999976,6330,1513,4.183740912095175,3,0,0,True
|
||||
simple_qa_00042,simple_qa,answering,1454.4789999999991,5313,1358,3.9123711340206184,3,0,0,True
|
||||
simple_qa_00043,simple_qa,answering,1366.8249999999987,5530,733,7.544338335607094,3,0,0,True
|
||||
simple_qa_00044,simple_qa,answering,1134.8300000000008,5574,919,6.065288356909685,3,0,0,True
|
||||
simple_qa_00045,simple_qa,answering,1290.6880000000028,8607,1321,6.51551854655564,5,1,0,True
|
||||
simple_qa_00046,simple_qa,answering,887.5910000000005,5342,1220,4.378688524590164,3,0,0,True
|
||||
simple_qa_00047,simple_qa,answering,1500.1400000000017,11544,1496,7.716577540106952,5,0,0,True
|
||||
simple_qa_00048,simple_qa,answering,590.2030000000025,3429,1270,2.7,3,0,0,True
|
||||
simple_qa_00049,simple_qa,answering,1328.8580000000038,3926,1557,2.5215157353885678,3,0,0,True
|
||||
simple_qa_00050,simple_qa,answering,895.7130000000006,4332,1319,3.284306292645944,3,0,0,True
|
||||
simple_qa_00051,simple_qa,answering,754.6930000000032,6203,1342,4.62220566318927,3,0,0,True
|
||||
simple_qa_00052,simple_qa,answering,1541.4049999999975,5071,1117,4.539838854073411,3,0,0,True
|
||||
simple_qa_00053,simple_qa,answering,1177.0819999999985,8016,1230,6.517073170731707,5,1,0,True
|
||||
simple_qa_00054,simple_qa,answering,498.7519999999961,5493,391,14.048593350383632,3,0,0,True
|
||||
simple_qa_00055,simple_qa,answering,1162.9900000000007,7303,1651,4.423379769836463,3,0,0,True
|
||||
simple_qa_00056,simple_qa,answering,674.510000000005,2802,669,4.188340807174888,3,0,0,True
|
||||
simple_qa_00057,simple_qa,answering,2256.7659999999987,4338,969,4.476780185758514,3,0,0,True
|
||||
simple_qa_00058,simple_qa,answering,1575.8580000000038,10725,3214,3.336963285625389,5,1,0,True
|
||||
simple_qa_00059,simple_qa,answering,1815.6789999999958,5774,1265,4.564426877470356,3,0,0,True
|
||||
simple_qa_00060,simple_qa,answering,686.0010000000045,5624,923,6.0931744312026,3,0,0,True
|
||||
simple_qa_00061,simple_qa,answering,1254.2200000000037,6000,887,6.764374295377678,3,0,0,True
|
||||
simple_qa_00062,simple_qa,answering,945.3009999999936,7475,564,13.25354609929078,3,0,0,True
|
||||
simple_qa_00063,simple_qa,answering,841.0459999999987,3683,751,4.9041278295605855,3,0,0,True
|
||||
simple_qa_00064,simple_qa,answering,1241.6660000000022,9729,904,10.76216814159292,5,1,0,True
|
||||
simple_qa_00065,simple_qa,answering,1516.855999999997,6629,1109,5.977457168620378,5,1,0,True
|
||||
simple_qa_00066,simple_qa,answering,1183.698999999997,3552,1627,2.183159188690842,3,0,0,True
|
||||
simple_qa_00067,simple_qa,answering,995.9650000000054,8377,2106,3.977682811016144,3,0,0,True
|
||||
simple_qa_00068,simple_qa,answering,959.3050000000005,4731,1465,3.2293515358361775,3,0,0,True
|
||||
simple_qa_00069,simple_qa,answering,1188.1830000000023,3612,1113,3.2452830188679247,3,0,0,True
|
||||
simple_qa_00070,simple_qa,answering,1491.27,4065,761,5.341655716162943,3,0,0,True
|
||||
simple_qa_00071,simple_qa,answering,846.0699999999974,2898,1350,2.1466666666666665,3,0,0,True
|
||||
simple_qa_00072,simple_qa,answering,1207.8729999999994,3417,747,4.57429718875502,3,0,0,True
|
||||
simple_qa_00073,simple_qa,answering,1940.8279999999963,7028,3264,2.153186274509804,5,1,0,True
|
||||
simple_qa_00074,simple_qa,answering,1482.2769999999964,5076,1081,4.695652173913044,3,0,0,True
|
||||
simple_qa_00075,simple_qa,answering,864.4090000000019,6816,897,7.59866220735786,3,0,0,True
|
||||
simple_qa_00076,simple_qa,answering,1091.8100000000024,4841,1310,3.6954198473282442,3,0,0,True
|
||||
simple_qa_00077,simple_qa,answering,1149.9900000000025,4287,737,5.8168249660786975,3,0,0,True
|
||||
simple_qa_00078,simple_qa,answering,1253.6500000000003,6102,1037,5.884281581485053,3,0,0,True
|
||||
simple_qa_00079,simple_qa,answering,2618.4089999999997,6982,680,10.26764705882353,5,1,0,True
|
||||
simple_qa_00080,simple_qa,answering,838.6209999999962,5148,824,6.247572815533981,3,0,0,True
|
||||
simple_qa_00081,simple_qa,answering,706.4880000000003,8520,643,13.250388802488336,3,0,0,True
|
||||
simple_qa_00082,simple_qa,answering,1185.3399999999965,4372,474,9.223628691983123,3,0,0,True
|
||||
simple_qa_00083,simple_qa,answering,1010.4350000000011,8796,1347,6.5300668151447665,3,0,0,True
|
||||
simple_qa_00084,simple_qa,answering,652.358999999997,3394,1270,2.6724409448818895,3,0,0,True
|
||||
simple_qa_00085,simple_qa,answering,1272.1099999999979,5066,1257,4.030230708035004,3,0,0,True
|
||||
simple_qa_00086,simple_qa,answering,1247.2220000000007,7260,610,11.901639344262295,5,1,0,True
|
||||
simple_qa_00087,simple_qa,answering,813.3010000000027,3990,2088,1.910919540229885,3,0,0,True
|
||||
simple_qa_00088,simple_qa,answering,1376.7839999999935,2576,1292,1.9938080495356036,3,0,0,True
|
||||
simple_qa_00089,simple_qa,answering,727.212999999999,5616,1291,4.350116189000775,3,0,0,True
|
||||
simple_qa_00090,simple_qa,answering,1237.8660000000039,7402,851,8.698002350176264,3,0,0,True
|
||||
simple_qa_00091,simple_qa,answering,757.8150000000007,9526,1514,6.291941875825628,5,1,0,True
|
||||
simple_qa_00092,simple_qa,answering,2362.844000000003,4959,1026,4.833333333333333,3,0,0,True
|
||||
simple_qa_00093,simple_qa,answering,1152.037,4596,920,4.995652173913044,3,0,0,True
|
||||
simple_qa_00094,simple_qa,answering,1841.4469999999951,4404,1581,2.7855787476280836,3,0,0,True
|
||||
simple_qa_00095,simple_qa,answering,1221.4370000000017,5886,1182,4.979695431472082,3,0,0,True
|
||||
simple_qa_00096,simple_qa,answering,1167.4190000000024,5641,2854,1.9765241765942536,3,0,0,True
|
||||
simple_qa_00097,simple_qa,answering,1575.9909999999948,4913,1439,3.414176511466296,3,0,0,True
|
||||
simple_qa_00098,simple_qa,answering,1244.641999999999,8507,1101,7.72661217075386,3,0,0,True
|
||||
simple_qa_00099,simple_qa,answering,1048.887999999998,4661,1839,2.5345296356715608,3,0,0,True
|
||||
tool_research_00000,tool_research,evidence_collection,2194.9050000000057,24867,3202,7.766083697688944,5,1,0,True
|
||||
tool_research_00001,tool_research,evidence_collection,3702.2710000000034,43758,1917,22.826291079812208,9,2,0,True
|
||||
tool_research_00002,tool_research,evidence_collection,4914.04399999999,29867,1906,15.669989506820567,5,1,0,True
|
||||
tool_research_00003,tool_research,evidence_collection,2975.851999999996,18814,4275,4.40093567251462,5,1,0,True
|
||||
tool_research_00004,tool_research,evidence_collection,1859.4280000000012,17926,1263,14.193190815518607,3,0,0,True
|
||||
tool_research_00005,tool_research,evidence_collection,1666.4189999999976,13686,8729,1.56787719097262,5,1,0,True
|
||||
tool_research_00006,tool_research,evidence_collection,2696.655000000007,9331,1703,5.479154433352907,3,0,0,True
|
||||
tool_research_00007,tool_research,evidence_collection,5450.783000000001,13849,1654,8.373035066505441,6,2,1,True
|
||||
tool_research_00008,tool_research,evidence_collection,1531.513000000004,17238,3296,5.22997572815534,5,1,0,True
|
||||
tool_research_00009,tool_research,evidence_collection,4081.8340000000007,13926,436,31.940366972477065,5,1,0,True
|
||||
tool_research_00010,tool_research,evidence_collection,4327.119000000011,41953,2235,18.770917225950782,5,1,0,True
|
||||
tool_research_00011,tool_research,evidence_collection,3781.2230000000113,15091,3794,3.977596204533474,5,1,0,True
|
||||
tool_research_00012,tool_research,evidence_collection,1917.4310000000078,14626,1784,8.198430493273543,3,0,0,True
|
||||
tool_research_00013,tool_research,evidence_collection,3997.425000000007,13485,1603,8.412351840299438,5,1,0,True
|
||||
tool_research_00014,tool_research,evidence_collection,2441.9809999999984,36453,2047,17.80801172447484,5,1,0,True
|
||||
tool_research_00015,tool_research,evidence_collection,3959.5280000000057,15873,1390,11.419424460431655,3,0,0,True
|
||||
tool_research_00016,tool_research,evidence_collection,1198.003,13816,976,14.155737704918034,3,0,0,True
|
||||
tool_research_00017,tool_research,evidence_collection,4552.255999999999,16333,2462,6.634037367993502,5,1,0,True
|
||||
tool_research_00018,tool_research,evidence_collection,6950.037999999992,39260,5865,6.693947144075021,6,2,1,True
|
||||
tool_research_00019,tool_research,evidence_collection,3067.522999999994,15009,2037,7.368188512518409,3,0,0,True
|
||||
tool_research_00020,tool_research,evidence_collection,4835.037999999997,30787,1662,18.524067388688326,7,1,0,True
|
||||
tool_research_00021,tool_research,evidence_collection,8310.215999999997,113647,4305,26.39883855981417,17,4,0,True
|
||||
tool_research_00022,tool_research,evidence_collection,3200.504999999993,18179,1048,17.346374045801525,5,1,0,True
|
||||
tool_research_00023,tool_research,evidence_collection,13355.828000000003,126809,1205,105.2356846473029,15,5,1,True
|
||||
tool_research_00024,tool_research,evidence_collection,3643.411999999998,21779,2025,10.755061728395061,5,1,0,True
|
||||
tool_research_00025,tool_research,evidence_collection,9670.201000000006,47663,1365,34.91794871794872,13,4,2,True
|
||||
tool_research_00026,tool_research,evidence_collection,1291.9939999999883,12623,3997,3.1581185889417065,3,0,0,True
|
||||
tool_research_00027,tool_research,evidence_collection,4673.997999999998,27499,1513,18.17514871116986,5,1,0,True
|
||||
tool_research_00028,tool_research,evidence_collection,2161.7999999999993,32414,1401,23.13633119200571,5,1,0,True
|
||||
tool_research_00029,tool_research,evidence_collection,5903.75499999999,21437,3963,5.40928589452435,5,1,0,True
|
||||
tool_research_00030,tool_research,evidence_collection,4832.2890000000025,62170,2517,24.70003972983711,9,2,0,True
|
||||
tool_research_00031,tool_research,evidence_collection,4330.880000000007,29507,2884,10.23127600554785,6,2,1,True
|
||||
tool_research_00032,tool_research,evidence_collection,1570.5789999999952,18174,849,21.406360424028268,5,1,0,True
|
||||
tool_research_00033,tool_research,evidence_collection,1797.4840000000113,34726,2226,15.600179694519317,5,1,0,True
|
||||
tool_research_00034,tool_research,evidence_collection,3040.871999999993,19123,2094,9.13228271251194,5,1,0,True
|
||||
tool_research_00035,tool_research,evidence_collection,2986.626000000001,24572,1303,18.858019953952418,5,1,0,True
|
||||
tool_research_00036,tool_research,evidence_collection,3130.6490000000053,28061,1577,17.793912492073556,3,0,0,True
|
||||
tool_research_00037,tool_research,evidence_collection,3123.7370000000055,22728,3665,6.201364256480218,5,1,0,True
|
||||
tool_research_00038,tool_research,evidence_collection,1708.3070000000048,29910,1078,27.74582560296846,5,1,0,True
|
||||
tool_research_00039,tool_research,evidence_collection,4255.195999999998,21270,1412,15.063739376770538,5,1,0,True
|
||||
tool_research_00040,tool_research,evidence_collection,2188.941,24341,4087,5.955713237093223,5,1,0,True
|
||||
tool_research_00041,tool_research,evidence_collection,2437.484999999995,4248,1853,2.2924986508364813,3,0,0,True
|
||||
tool_research_00042,tool_research,evidence_collection,2187.698999999995,8817,2395,3.681419624217119,3,0,0,True
|
||||
tool_research_00043,tool_research,evidence_collection,5124.787999999995,36771,2156,17.055194805194805,9,2,0,True
|
||||
tool_research_00044,tool_research,evidence_collection,2136.277000000007,23014,3951,5.824854467223488,5,1,0,True
|
||||
tool_research_00045,tool_research,evidence_collection,2712.2329999999974,13715,4904,2.7966965742251224,5,1,0,True
|
||||
tool_research_00046,tool_research,evidence_collection,2093.755999999999,27149,2497,10.872647176611935,3,0,0,True
|
||||
tool_research_00047,tool_research,evidence_collection,3331.8359999999957,10694,2450,4.364897959183674,3,0,0,True
|
||||
tool_research_00048,tool_research,evidence_collection,2496.739000000005,23797,420,56.65952380952381,5,1,0,True
|
||||
tool_research_00049,tool_research,evidence_collection,3162.072999999992,37174,6914,5.376627133352618,5,1,0,True
|
||||
tool_research_00050,tool_research,evidence_collection,3349.9610000000075,20453,1503,13.608117099135063,5,1,0,True
|
||||
tool_research_00051,tool_research,evidence_collection,2585.735999999997,20752,4970,4.175452716297786,5,1,0,True
|
||||
tool_research_00052,tool_research,evidence_collection,2241.700999999992,18226,1014,17.974358974358974,5,1,0,True
|
||||
tool_research_00053,tool_research,evidence_collection,1681.621000000007,20527,1964,10.451629327902241,5,1,0,True
|
||||
tool_research_00054,tool_research,evidence_collection,4616.5809999999965,14793,1020,14.50294117647059,5,1,0,True
|
||||
tool_research_00055,tool_research,evidence_collection,1986.9599999999964,36674,1499,24.46564376250834,5,1,0,True
|
||||
tool_research_00056,tool_research,evidence_collection,3329.991000000007,21611,2138,10.108044901777362,5,1,0,True
|
||||
tool_research_00057,tool_research,evidence_collection,1935.023000000001,11508,3856,2.9844398340248963,3,0,0,True
|
||||
tool_research_00058,tool_research,evidence_collection,2901.527999999999,31197,1663,18.759470835838844,5,1,0,True
|
||||
tool_research_00059,tool_research,evidence_collection,3321.638000000007,11370,816,13.933823529411764,3,0,0,True
|
||||
tool_research_00060,tool_research,evidence_collection,3683.4269999999947,22492,1908,11.78825995807128,5,1,0,True
|
||||
tool_research_00061,tool_research,evidence_collection,2848.731999999998,18988,1760,10.788636363636364,5,1,0,True
|
||||
tool_research_00062,tool_research,evidence_collection,2672.6560000000036,11461,1837,6.238976592270006,5,1,0,True
|
||||
tool_research_00063,tool_research,evidence_collection,2669.6290000000004,12186,2987,4.079678607298293,3,0,0,True
|
||||
tool_research_00064,tool_research,evidence_collection,1733.4749999999985,20624,2281,9.041648399824638,5,1,0,True
|
||||
tool_research_00065,tool_research,evidence_collection,1969.7800000000002,37289,2064,18.066375968992247,5,1,0,True
|
||||
tool_research_00066,tool_research,evidence_collection,2515.674000000004,27763,948,29.285864978902953,5,1,0,True
|
||||
tool_research_00067,tool_research,evidence_collection,3096.862999999999,25812,1096,23.55109489051095,5,1,0,True
|
||||
tool_research_00068,tool_research,evidence_collection,2049.244999999999,27451,1646,16.677399756986635,5,1,0,True
|
||||
tool_research_00069,tool_research,evidence_collection,1731.0909999999922,25997,2954,8.800609343263371,5,1,0,True
|
||||
tool_research_00070,tool_research,evidence_collection,3312.636999999995,31567,3135,10.069218500797447,5,1,0,True
|
||||
tool_research_00071,tool_research,evidence_collection,1862.328000000005,20908,2780,7.520863309352518,5,1,0,True
|
||||
tool_research_00072,tool_research,evidence_collection,3047.896000000009,54132,1025,52.81170731707317,5,1,0,True
|
||||
tool_research_00073,tool_research,evidence_collection,2561.8630000000026,21435,4790,4.474947807933194,5,1,0,True
|
||||
tool_research_00074,tool_research,evidence_collection,4560.357999999994,79773,2385,33.44779874213837,13,3,0,True
|
||||
tool_research_00075,tool_research,evidence_collection,3243.395000000007,7843,2993,2.6204477113264284,3,0,0,True
|
||||
tool_research_00076,tool_research,evidence_collection,2738.9289999999987,23031,2795,8.240071556350626,5,1,0,True
|
||||
tool_research_00077,tool_research,evidence_collection,5143.501999999998,26921,3689,7.297641637300082,3,0,0,True
|
||||
tool_research_00078,tool_research,evidence_collection,2541.331999999997,10770,5383,2.000743080066877,3,0,0,True
|
||||
tool_research_00079,tool_research,evidence_collection,4596.682000000002,30560,3128,9.769820971867007,9,2,0,True
|
||||
tool_research_00080,tool_research,evidence_collection,2516.4350000000013,10007,1693,5.910809214412286,3,0,0,True
|
||||
tool_research_00081,tool_research,evidence_collection,3084.7260000000033,17944,830,21.619277108433735,5,1,0,True
|
||||
tool_research_00082,tool_research,evidence_collection,2914.749999999998,25400,982,25.865580448065174,5,1,0,True
|
||||
tool_research_00083,tool_research,evidence_collection,2230.4889999999914,24604,2144,11.475746268656716,5,1,0,True
|
||||
tool_research_00084,tool_research,evidence_collection,3443.204000000009,24850,739,33.62652232746955,5,1,0,True
|
||||
tool_research_00085,tool_research,evidence_collection,5764.497000000006,31697,6531,4.853314959424284,6,2,1,True
|
||||
tool_research_00086,tool_research,evidence_collection,2663.731999999996,14968,967,15.478800413650465,5,1,0,True
|
||||
tool_research_00087,tool_research,evidence_collection,1660.2049999999906,10680,3250,3.286153846153846,5,1,0,True
|
||||
tool_research_00088,tool_research,evidence_collection,1999.1580000000085,11601,3306,3.5090744101633393,3,0,0,True
|
||||
tool_research_00089,tool_research,evidence_collection,2695.4450000000065,10711,3265,3.280551301684533,5,1,0,True
|
||||
tool_research_00090,tool_research,evidence_collection,5276.9389999999985,15851,1980,8.005555555555556,5,1,0,True
|
||||
tool_research_00091,tool_research,evidence_collection,5764.26699999999,27062,2151,12.581125058112505,6,2,1,True
|
||||
tool_research_00092,tool_research,evidence_collection,1482.0979999999936,17916,936,19.141025641025642,5,1,0,True
|
||||
tool_research_00093,tool_research,evidence_collection,2160.2140000000104,36749,2052,17.908869395711502,5,1,0,True
|
||||
tool_research_00094,tool_research,evidence_collection,3420.692000000017,15674,8252,1.8994183228308288,3,0,0,True
|
||||
tool_research_00095,tool_research,evidence_collection,1882.05099999999,19776,2123,9.315120113047573,5,1,0,True
|
||||
tool_research_00096,tool_research,evidence_collection,3586.549000000005,36710,1309,28.044308632543927,5,1,0,True
|
||||
tool_research_00097,tool_research,evidence_collection,1987.364999999997,14435,3124,4.62067861715749,5,1,0,True
|
||||
tool_research_00098,tool_research,evidence_collection,3917.211000000009,16232,1378,11.779390420899855,6,2,1,True
|
||||
tool_research_00099,tool_research,evidence_collection,4009.145999999987,74407,2235,33.2917225950783,5,1,0,True
|
||||
|
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
Binary file not shown.
|
After Width: | Height: | Size: 48 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 112 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 87 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 144 KiB |
@@ -0,0 +1,183 @@
|
||||
{
|
||||
"global": {
|
||||
"transition_probabilities": {
|
||||
"CallTool->Think": 0.9891472868217054,
|
||||
"Idle->Think": 0.9911167512690355,
|
||||
"Retry->CallTool": 0.9176470588235294,
|
||||
"Think->CallAgent": 0.12293086660175268,
|
||||
"Think->CallTool": 0.15603700097370984,
|
||||
"Think->Failed": 0.0017039922103213243,
|
||||
"Think->Send": 0.5148490749756572,
|
||||
"Think->Split": 0.20374878286270692,
|
||||
"Wait->Failed": 0.36363636363636365
|
||||
},
|
||||
"duration_ms": {
|
||||
"mean": 285.679917634447,
|
||||
"std": 550.6643665581886,
|
||||
"cv": 1.9275571454862042,
|
||||
"p50": 8.0,
|
||||
"p95": 1323.2897999999977,
|
||||
"count": 5597
|
||||
},
|
||||
"message_size_bytes": {
|
||||
"mean": 5570.409505092013,
|
||||
"std": 6586.248171004335,
|
||||
"cv": 1.1823633729232519,
|
||||
"p50": 3158.0,
|
||||
"p95": 18393.199999999997,
|
||||
"count": 5597
|
||||
}
|
||||
},
|
||||
"task_types": {
|
||||
"collaborative_analysis": {
|
||||
"phase": "multi_agent_synthesis",
|
||||
"task_count": 260,
|
||||
"tool_probability": 0.4806201550387597,
|
||||
"split_probability": 0.8192307692307692,
|
||||
"mean_subtasks": 2.976923076923077,
|
||||
"retry_probability": 0.12470588235294118,
|
||||
"mean_retries_if_any": 1.1627906976744187,
|
||||
"failure_probability": 0.007692307692307693,
|
||||
"think_time_ms": {
|
||||
"mean": 1012.4040078828829,
|
||||
"std": 819.189229985454,
|
||||
"cv": 0.8091524960460444,
|
||||
"p50": 802.0150000000001,
|
||||
"p95": 2609.3335999999995,
|
||||
"count": 888
|
||||
},
|
||||
"external_size_bytes": {
|
||||
"mean": 4103.692307692308,
|
||||
"std": 3820.340621837784,
|
||||
"cv": 0.9309520147688984,
|
||||
"p50": 3039.5,
|
||||
"p95": 11107.699999999995,
|
||||
"count": 260
|
||||
},
|
||||
"request_size_bytes": {
|
||||
"mean": 3936.623019182652,
|
||||
"std": 3891.679972776879,
|
||||
"cv": 0.9885833501997089,
|
||||
"p50": 2796.0,
|
||||
"p95": 10800.3,
|
||||
"count": 1199
|
||||
},
|
||||
"response_size_bytes": {
|
||||
"mean": 11829.127142857144,
|
||||
"std": 8952.816088861513,
|
||||
"cv": 0.7568450301312002,
|
||||
"p50": 9558.5,
|
||||
"p95": 29122.249999999993,
|
||||
"count": 1400
|
||||
},
|
||||
"message_count_per_task": {
|
||||
"mean": 11.01923076923077,
|
||||
"std": 5.376910696585285,
|
||||
"cv": 0.48795699166218987,
|
||||
"p50": 10.0,
|
||||
"p95": 21.049999999999983,
|
||||
"count": 260
|
||||
}
|
||||
},
|
||||
"simple_qa": {
|
||||
"phase": "answering",
|
||||
"task_count": 260,
|
||||
"tool_probability": 0.13740458015267176,
|
||||
"split_probability": 0.03461538461538462,
|
||||
"mean_subtasks": 1.0076923076923077,
|
||||
"retry_probability": 0.02702702702702703,
|
||||
"mean_retries_if_any": 1.0,
|
||||
"failure_probability": 0.0,
|
||||
"think_time_ms": {
|
||||
"mean": 315.74304316546767,
|
||||
"std": 193.59344702605458,
|
||||
"cv": 0.6131360649634342,
|
||||
"p50": 262.062,
|
||||
"p95": 693.3605,
|
||||
"count": 556
|
||||
},
|
||||
"external_size_bytes": {
|
||||
"mean": 1285.7846153846153,
|
||||
"std": 562.841233039538,
|
||||
"cv": 0.43774145864327046,
|
||||
"p50": 1167.5,
|
||||
"p95": 2332.1,
|
||||
"count": 260
|
||||
},
|
||||
"request_size_bytes": {
|
||||
"mean": 1646.314381270903,
|
||||
"std": 819.0778288985601,
|
||||
"cv": 0.4975221247027301,
|
||||
"p50": 1537.0,
|
||||
"p95": 3065.4999999999995,
|
||||
"count": 299
|
||||
},
|
||||
"response_size_bytes": {
|
||||
"mean": 1909.388888888889,
|
||||
"std": 1208.6473367395993,
|
||||
"cv": 0.6330021839830309,
|
||||
"p50": 1577.5,
|
||||
"p95": 4346.099999999999,
|
||||
"count": 558
|
||||
},
|
||||
"message_count_per_task": {
|
||||
"mean": 4.296153846153846,
|
||||
"std": 0.7184281823915581,
|
||||
"cv": 0.16722589742328123,
|
||||
"p50": 4.0,
|
||||
"p95": 6.0,
|
||||
"count": 260
|
||||
}
|
||||
},
|
||||
"tool_research": {
|
||||
"phase": "evidence_collection",
|
||||
"task_count": 260,
|
||||
"tool_probability": 0.7631578947368421,
|
||||
"split_probability": 0.2076923076923077,
|
||||
"mean_subtasks": 1.1692307692307693,
|
||||
"retry_probability": 0.09019607843137255,
|
||||
"mean_retries_if_any": 1.0952380952380953,
|
||||
"failure_probability": 0.0038461538461538464,
|
||||
"think_time_ms": {
|
||||
"mean": 660.7411426666666,
|
||||
"std": 548.0475005635645,
|
||||
"cv": 0.8294435826286146,
|
||||
"p50": 513.7415,
|
||||
"p95": 1615.4994999999997,
|
||||
"count": 750
|
||||
},
|
||||
"external_size_bytes": {
|
||||
"mean": 2591.223076923077,
|
||||
"std": 1938.9205968801086,
|
||||
"cv": 0.7482646377101818,
|
||||
"p50": 2023.0,
|
||||
"p95": 6498.299999999999,
|
||||
"count": 260
|
||||
},
|
||||
"request_size_bytes": {
|
||||
"mean": 2178.8425760286227,
|
||||
"std": 1869.411620553448,
|
||||
"cv": 0.8579837942954215,
|
||||
"p50": 1586.0,
|
||||
"p95": 6085.500000000001,
|
||||
"count": 559
|
||||
},
|
||||
"response_size_bytes": {
|
||||
"mean": 6327.029003783102,
|
||||
"std": 4973.701881543845,
|
||||
"cv": 0.7861038535732859,
|
||||
"p50": 4987.0,
|
||||
"p95": 15569.8,
|
||||
"count": 793
|
||||
},
|
||||
"message_count_per_task": {
|
||||
"mean": 6.211538461538462,
|
||||
"std": 2.097035805988451,
|
||||
"cv": 0.33760328765139147,
|
||||
"p50": 6.0,
|
||||
"p95": 11.0,
|
||||
"count": 260
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,26 @@
|
||||
timeout_probability,max_retries,success_rate,mean_retries,mean_amplification,mean_latency_ms
|
||||
0.0,0,1.0,0.0,9.791625846103754,1611.6456398964472
|
||||
0.0,1,1.0,0.0,9.929872318854873,1810.7223041670222
|
||||
0.0,2,1.0,0.0,8.566505830883267,1646.5055480731012
|
||||
0.0,3,1.0,0.0,9.466712608627542,1652.6593639522055
|
||||
0.0,5,1.0,0.0,9.662682945914268,1756.6494872943697
|
||||
0.03,0,0.9625,0.0,9.236763247092442,1764.2494023015984
|
||||
0.03,1,1.0,0.016666666666666666,9.49838873538483,1668.745910772185
|
||||
0.03,2,1.0,0.0375,9.40180231370975,1753.199216159701
|
||||
0.03,3,1.0,0.016666666666666666,10.022457643868133,1860.8835997078063
|
||||
0.03,5,1.0,0.025,9.019935163210244,1900.697800739017
|
||||
0.08,0,0.9291666666666667,0.0,9.92154310687105,1719.1310133789257
|
||||
0.08,1,0.9958333333333333,0.05416666666666667,9.48779578533714,1843.49537077021
|
||||
0.08,2,0.9958333333333333,0.07083333333333333,9.542258282931957,1902.6419815786642
|
||||
0.08,3,1.0,0.05,9.887456874772154,1817.7727139655656
|
||||
0.08,5,1.0,0.09166666666666666,9.097284092135592,1904.8547916418988
|
||||
0.15,0,0.8541666666666666,0.0,8.835720371687312,1571.6219931658118
|
||||
0.15,1,0.9791666666666666,0.09583333333333334,9.122618265595515,1955.8897478710594
|
||||
0.15,2,1.0,0.10833333333333334,9.846728400807162,1980.994814000937
|
||||
0.15,3,1.0,0.12083333333333333,9.51555007863001,1950.3948320063673
|
||||
0.15,5,1.0,0.19166666666666668,10.257406318574677,2173.315967936333
|
||||
0.25,0,0.8333333333333334,0.0,8.62914384683803,1654.824555364319
|
||||
0.25,1,0.9541666666666667,0.16666666666666666,8.984142037708278,2090.160252075161
|
||||
0.25,2,0.9875,0.2625,9.642823436259429,2393.4294606209505
|
||||
0.25,3,1.0,0.22916666666666666,8.7946687060034,2226.263869969628
|
||||
0.25,5,1.0,0.19583333333333333,9.066500470500229,2110.276874421043
|
||||
|
@@ -0,0 +1,9 @@
|
||||
arrival_rate,offered_tasks,completed_tasks,throughput_per_second,mean_delay_ms,p95_delay_ms,queue_peak,drop_rate,success_rate,mean_amplification
|
||||
0.5,98,85,0.53125,5789.822235500761,12757.162733844745,5,0.0,1.0,31.470196724444556
|
||||
1.0,176,160,1.0,31384.496417526076,42781.94943988779,34,0.0,1.0,31.986629448479086
|
||||
2.0,352,317,1.98125,153100.48173718844,266221.0600580607,211,0.0,0.9968454258675079,27.062374263992844
|
||||
4.0,687,574,3.5875,371545.11383159773,654462.4416805771,500,0.06841339155749636,1.0,32.343350031249344
|
||||
6.0,1095,518,3.2375,403282.1583010225,624405.7892324593,500,0.410958904109589,0.9980694980694981,28.847411906142742
|
||||
8.0,1433,477,2.98125,453122.6068650545,634995.5685232729,500,0.5422191207257502,1.0,28.88759065286518
|
||||
10.0,1829,465,2.90625,460685.0783967892,629246.0471832517,500,0.644614543466375,0.9978494623655914,29.343167280152798
|
||||
12.0,2201,410,2.5625,502425.69206713024,633541.2012092929,500,0.7019536574284416,0.9975609756097561,31.051514679264738
|
||||
|
@@ -0,0 +1,18 @@
|
||||
{
|
||||
"best_model_by_internal_bytes_mape": {
|
||||
"model": "full_model",
|
||||
"metric": "internal_bytes",
|
||||
"mae": 8514.790993271408,
|
||||
"rmse": 10202.035682525451,
|
||||
"mape_percent": 25.132613550059535
|
||||
},
|
||||
"best_model_by_latency_mape": {
|
||||
"model": "full_model",
|
||||
"metric": "latency_ms",
|
||||
"mae": 1740.55513184213,
|
||||
"rmse": 2061.3161939037764,
|
||||
"mape_percent": 42.13888590021146
|
||||
},
|
||||
"max_stress_arrival_rate": 12.0,
|
||||
"max_observed_p95_delay_ms": 654462.4416805771
|
||||
}
|
||||
@@ -0,0 +1,16 @@
|
||||
model,metric,mae,rmse,mape_percent
|
||||
full_model,internal_bytes,8514.790993271408,10202.035682525451,25.132613550059535
|
||||
full_model,latency_ms,1740.55513184213,2061.3161939037764,42.13888590021146
|
||||
full_model,message_count,0.24833333333333366,0.34639011404933506,4.4460827599229225
|
||||
full_model,tool_calls,0.0977777777777778,0.12750453877179202,8.967944987269812
|
||||
full_model,amplification,2.1844309474987855,3.1463454795356744,17.403062466244346
|
||||
no_context,internal_bytes,28106.101475356598,38300.17877551533,107.12005537801083
|
||||
no_context,latency_ms,3059.4684226124723,4030.5538811505185,68.83144127074493
|
||||
no_context,message_count,2.332777777777778,3.1734000051352798,34.22052281701404
|
||||
no_context,tool_calls,0.645,0.7287946670130528,188.58078578942232
|
||||
no_context,amplification,10.861414695027626,13.961977843833159,67.33834604907454
|
||||
static_mean,internal_bytes,29834.93333333333,32709.783175317236,230.39064998346973
|
||||
static_mean,latency_ms,2757.6886622222223,3058.6901465213614,119.58343818448623
|
||||
static_mean,message_count,2.5155555555555558,2.7855500155066126,48.03496553983882
|
||||
static_mean,tool_calls,0.5444444444444444,0.6355225321645873,264.95059144468667
|
||||
static_mean,amplification,10.71876769134868,12.026846682885607,111.10365289444462
|
||||
|
@@ -0,0 +1,10 @@
|
||||
task_type,model,actual_internal_bytes,predicted_internal_bytes,actual_latency_ms,predicted_latency_ms,actual_message_count,predicted_message_count,actual_tool_calls,predicted_tool_calls,actual_amplification,predicted_amplification
|
||||
collaborative_analysis,static_mean,82782.45,38030.049999999996,8428.771760000001,4292.238766666668,9.88,6.1066666666666665,1.66,0.9266666666666667,33.798140646040636,17.719989109017618
|
||||
collaborative_analysis,no_context,82782.45,17953.655088125477,8428.771760000001,1674.760201302985,9.88,4.575,1.66,0.55,33.798140646040636,10.538207426716697
|
||||
collaborative_analysis,full_model,82782.45,68099.5326730428,8428.771760000001,5276.731101216728,9.88,9.741666666666667,1.66,1.75,33.798140646040636,33.290090674565
|
||||
simple_qa,static_mean,5514.23,38030.049999999996,1128.43623,4292.238766666668,3.24,6.1066666666666665,0.11,0.9266666666666667,4.875984197964249,17.719989109017618
|
||||
simple_qa,no_context,5514.23,17261.226304896398,1128.43623,2040.1508029795593,3.24,4.65,0.11,0.625,4.875984197964249,9.934747754184363
|
||||
simple_qa,full_model,5514.23,4423.486362645099,1128.43623,672.4328817972068,3.24,3.216666666666667,0.11,0.10833333333333334,4.875984197964249,4.216398328357828
|
||||
tool_research,static_mean,25793.47,38030.049999999996,3319.5083100000024,4292.238766666668,5.2,6.1066666666666665,1.01,0.9266666666666667,14.485842483047964,17.719989109017618
|
||||
tool_research,no_context,25793.47,18050.956790701126,3319.5083100000024,1806.829173839162,5.2,4.916666666666667,1.01,0.7,14.485842483047964,10.22029517350914
|
||||
tool_research,full_model,25793.47,16022.75798449787,3319.5083100000024,1705.8869214596782,5.2,4.616666666666666,1.01,0.8083333333333333,14.485842483047964,9.100185481633664
|
||||
|
@@ -0,0 +1,37 @@
|
||||
seed: 20260813
|
||||
|
||||
generation:
|
||||
train_tasks_per_type: 260
|
||||
test_tasks_per_type: 100
|
||||
task_types:
|
||||
- simple_qa
|
||||
- tool_research
|
||||
- collaborative_analysis
|
||||
llm:
|
||||
temperature: 0.5
|
||||
timeout_seconds: 90
|
||||
max_tokens: 3500
|
||||
|
||||
network:
|
||||
agent_count: 8
|
||||
tool_count: 3
|
||||
coordinator: agent_0
|
||||
default_link_bandwidth_mbps: 20
|
||||
default_link_delay_ms: 8
|
||||
max_concurrency: 4
|
||||
queue_capacity: 500
|
||||
|
||||
simulation:
|
||||
replications: 16
|
||||
timeout_ms: 2200
|
||||
max_retries: 2
|
||||
retry_backoff_ms: 180
|
||||
|
||||
experiments:
|
||||
validation_tasks_per_scenario: 120
|
||||
arrival_rates_per_second: [0.5, 1, 2, 4, 6, 8, 10, 12]
|
||||
stress_duration_seconds: 180
|
||||
stress_warmup_seconds: 20
|
||||
timeout_probabilities: [0.0, 0.03, 0.08, 0.15, 0.25]
|
||||
retry_limits: [0, 1, 2, 3, 5]
|
||||
|
||||
@@ -0,0 +1,52 @@
|
||||
{
|
||||
"metadata": {
|
||||
"generator": "local_builtin"
|
||||
},
|
||||
"profiles": [
|
||||
{
|
||||
"task_type": "simple_qa",
|
||||
"description": "单节点即可完成的简短问答，少量情况下调用工具。",
|
||||
"phase": "answering",
|
||||
"tool_probability": 0.1,
|
||||
"split_probability": 0.05,
|
||||
"mean_subtasks": 1.2,
|
||||
"timeout_probability": 0.02,
|
||||
"failure_probability": 0.01,
|
||||
"think_time_ms_mean": 420.0,
|
||||
"think_time_cv": 0.55,
|
||||
"request_size_bytes_mean": 1800.0,
|
||||
"response_size_bytes_mean": 2600.0,
|
||||
"message_size_cv": 0.45
|
||||
},
|
||||
{
|
||||
"task_type": "tool_research",
|
||||
"description": "需要搜索、数据库或工具结果的研究任务。",
|
||||
"phase": "evidence_collection",
|
||||
"tool_probability": 0.78,
|
||||
"split_probability": 0.2,
|
||||
"mean_subtasks": 1.8,
|
||||
"timeout_probability": 0.07,
|
||||
"failure_probability": 0.025,
|
||||
"think_time_ms_mean": 900.0,
|
||||
"think_time_cv": 0.75,
|
||||
"request_size_bytes_mean": 3200.0,
|
||||
"response_size_bytes_mean": 8500.0,
|
||||
"message_size_cv": 0.7
|
||||
},
|
||||
{
|
||||
"task_type": "collaborative_analysis",
|
||||
"description": "协调多个执行 Agent 并汇总结果的复杂分析任务。",
|
||||
"phase": "multi_agent_synthesis",
|
||||
"tool_probability": 0.48,
|
||||
"split_probability": 0.82,
|
||||
"mean_subtasks": 3.4,
|
||||
"timeout_probability": 0.09,
|
||||
"failure_probability": 0.035,
|
||||
"think_time_ms_mean": 1450.0,
|
||||
"think_time_cv": 0.85,
|
||||
"request_size_bytes_mean": 5200.0,
|
||||
"response_size_bytes_mean": 11800.0,
|
||||
"message_size_cv": 0.8
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -0,0 +1,301 @@
|
||||
task_id,task_type,task_phase,latency_ms,internal_bytes,input_bytes,amplification,message_count,tool_calls,retries,success
|
||||
collaborative_analysis_00000,collaborative_analysis,multi_agent_synthesis,6111.839000000004,62448,1205,51.824066390041494,7,1,0,True
|
||||
collaborative_analysis_00001,collaborative_analysis,multi_agent_synthesis,7858.875999999981,57236,2452,23.34257748776509,7,0,0,True
|
||||
collaborative_analysis_00002,collaborative_analysis,multi_agent_synthesis,3745.010999999977,36184,6916,5.231925968768074,5,1,0,True
|
||||
collaborative_analysis_00003,collaborative_analysis,multi_agent_synthesis,3370.6700000000183,15600,1146,13.612565445026178,3,0,0,True
|
||||
collaborative_analysis_00004,collaborative_analysis,multi_agent_synthesis,3970.753000000002,26927,5695,4.728182616330114,5,1,0,True
|
||||
collaborative_analysis_00005,collaborative_analysis,multi_agent_synthesis,3692.181000000005,9783,2845,3.438664323374341,3,0,0,True
|
||||
collaborative_analysis_00006,collaborative_analysis,multi_agent_synthesis,12027.614,101344,5088,19.91823899371069,9,1,0,True
|
||||
collaborative_analysis_00007,collaborative_analysis,multi_agent_synthesis,3174.7689999999975,13427,10177,1.3193475483934363,3,0,0,True
|
||||
collaborative_analysis_00008,collaborative_analysis,multi_agent_synthesis,4553.435000000008,106516,5924,17.98041863605672,13,2,0,True
|
||||
collaborative_analysis_00009,collaborative_analysis,multi_agent_synthesis,20393.187000000013,136393,8870,15.376888387824126,19,3,0,True
|
||||
collaborative_analysis_00010,collaborative_analysis,multi_agent_synthesis,9716.779000000002,43830,1420,30.866197183098592,9,2,0,True
|
||||
collaborative_analysis_00011,collaborative_analysis,multi_agent_synthesis,13658.126999999979,113877,6803,16.73923269145965,13,2,0,True
|
||||
collaborative_analysis_00012,collaborative_analysis,multi_agent_synthesis,5092.640999999986,138420,4391,31.523570940560237,13,2,0,True
|
||||
collaborative_analysis_00013,collaborative_analysis,multi_agent_synthesis,2393.601999999987,13198,8494,1.5538026842477042,3,0,0,True
|
||||
collaborative_analysis_00014,collaborative_analysis,multi_agent_synthesis,7330.83400000001,65750,876,75.05707762557077,11,2,0,True
|
||||
collaborative_analysis_00015,collaborative_analysis,multi_agent_synthesis,16492.502,180400,2157,83.63467779323133,23,3,0,True
|
||||
collaborative_analysis_00016,collaborative_analysis,multi_agent_synthesis,16875.831000000006,205302,2605,78.81074856046065,19,3,0,True
|
||||
collaborative_analysis_00017,collaborative_analysis,multi_agent_synthesis,9850.209000000006,147782,1988,74.33702213279678,19,3,0,True
|
||||
collaborative_analysis_00018,collaborative_analysis,multi_agent_synthesis,10007.738999999987,126126,4218,29.90184921763869,15,2,0,True
|
||||
collaborative_analysis_00019,collaborative_analysis,multi_agent_synthesis,11525.198999999986,106483,1192,89.33137583892618,7,1,0,True
|
||||
collaborative_analysis_00020,collaborative_analysis,multi_agent_synthesis,5159.906000000006,59557,2210,26.94886877828054,9,2,0,True
|
||||
collaborative_analysis_00021,collaborative_analysis,multi_agent_synthesis,4791.642999999994,57467,18445,3.1155868799132556,5,0,0,True
|
||||
collaborative_analysis_00022,collaborative_analysis,multi_agent_synthesis,11351.583000000006,75128,3315,22.663046757164405,9,1,0,True
|
||||
collaborative_analysis_00023,collaborative_analysis,multi_agent_synthesis,8277.253999999999,39603,5217,7.591144335825187,5,1,0,True
|
||||
collaborative_analysis_00024,collaborative_analysis,multi_agent_synthesis,19919.341000000004,167247,1166,143.43653516295026,23,5,0,True
|
||||
collaborative_analysis_00025,collaborative_analysis,multi_agent_synthesis,9099.73500000001,69536,6843,10.161625018266841,11,1,0,True
|
||||
collaborative_analysis_00026,collaborative_analysis,multi_agent_synthesis,3098.5450000000014,55189,7507,7.351671773011856,11,2,0,True
|
||||
collaborative_analysis_00027,collaborative_analysis,multi_agent_synthesis,6933.150000000012,128239,5952,21.545530913978496,13,3,0,True
|
||||
collaborative_analysis_00028,collaborative_analysis,multi_agent_synthesis,14684.41899999999,164414,1446,113.70262793914246,18,5,1,True
|
||||
collaborative_analysis_00029,collaborative_analysis,multi_agent_synthesis,22606.593000000004,130445,2700,48.31296296296296,13,3,2,True
|
||||
collaborative_analysis_00030,collaborative_analysis,multi_agent_synthesis,7566.215999999997,53530,2840,18.848591549295776,7,0,0,True
|
||||
collaborative_analysis_00031,collaborative_analysis,multi_agent_synthesis,9549.07,182717,560,326.28035714285716,11,2,0,True
|
||||
collaborative_analysis_00032,collaborative_analysis,multi_agent_synthesis,16413.354,140512,4336,32.40590405904059,13,1,0,True
|
||||
collaborative_analysis_00033,collaborative_analysis,multi_agent_synthesis,3107.8390000000127,25062,1526,16.42332896461337,3,0,0,True
|
||||
collaborative_analysis_00034,collaborative_analysis,multi_agent_synthesis,2382.689999999997,37813,4410,8.57437641723356,5,1,0,True
|
||||
collaborative_analysis_00035,collaborative_analysis,multi_agent_synthesis,6573.08900000001,42752,1231,34.72948822095857,9,2,0,True
|
||||
collaborative_analysis_00036,collaborative_analysis,multi_agent_synthesis,14503.11400000001,179234,7724,23.20481615743138,23,6,1,True
|
||||
collaborative_analysis_00037,collaborative_analysis,multi_agent_synthesis,6998.415999999992,40737,4407,9.243703199455412,5,1,0,True
|
||||
collaborative_analysis_00038,collaborative_analysis,multi_agent_synthesis,9218.387000000006,76646,5615,13.650222617987533,12,3,1,True
|
||||
collaborative_analysis_00039,collaborative_analysis,multi_agent_synthesis,14171.648999999974,82798,3958,20.919151086407275,13,2,0,True
|
||||
collaborative_analysis_00040,collaborative_analysis,multi_agent_synthesis,16203.926999999992,192384,4272,45.03370786516854,19,2,0,True
|
||||
collaborative_analysis_00041,collaborative_analysis,multi_agent_synthesis,8077.832999999999,86864,14703,5.907909950350269,9,1,0,True
|
||||
collaborative_analysis_00042,collaborative_analysis,multi_agent_synthesis,11980.147000000017,175669,4129,42.545168321627514,17,2,0,True
|
||||
collaborative_analysis_00043,collaborative_analysis,multi_agent_synthesis,8383.41299999999,86553,4556,18.99758560140474,11,1,0,True
|
||||
collaborative_analysis_00044,collaborative_analysis,multi_agent_synthesis,3781.3569999999854,21537,2248,9.580516014234876,5,1,0,True
|
||||
collaborative_analysis_00045,collaborative_analysis,multi_agent_synthesis,2871.480999999989,29178,3997,7.299974981235927,5,1,0,True
|
||||
collaborative_analysis_00046,collaborative_analysis,multi_agent_synthesis,1987.737999999979,21361,8073,2.6459804285891244,3,0,0,True
|
||||
collaborative_analysis_00047,collaborative_analysis,multi_agent_synthesis,10075.866999999987,219312,9941,22.061362036012472,17,3,0,True
|
||||
collaborative_analysis_00048,collaborative_analysis,multi_agent_synthesis,6179.957999999999,70354,2470,28.4834008097166,5,1,0,True
|
||||
collaborative_analysis_00049,collaborative_analysis,multi_agent_synthesis,3145.8080000000164,28609,4669,6.127436281859071,3,0,0,True
|
||||
collaborative_analysis_00050,collaborative_analysis,multi_agent_synthesis,6249.4649999999865,28317,882,32.105442176870746,7,1,0,True
|
||||
collaborative_analysis_00051,collaborative_analysis,multi_agent_synthesis,11702.425000000005,187198,1275,146.82196078431372,17,2,0,True
|
||||
collaborative_analysis_00052,collaborative_analysis,multi_agent_synthesis,10426.145999999988,122179,1403,87.08410548823949,13,2,0,True
|
||||
collaborative_analysis_00053,collaborative_analysis,multi_agent_synthesis,3776.5890000000013,10701,3073,3.482264887731858,3,0,0,True
|
||||
collaborative_analysis_00054,collaborative_analysis,multi_agent_synthesis,6411.059999999992,122716,3644,33.6761800219539,13,3,0,True
|
||||
collaborative_analysis_00055,collaborative_analysis,multi_agent_synthesis,9190.782999999981,87827,8202,10.707998049256279,13,1,0,True
|
||||
collaborative_analysis_00056,collaborative_analysis,multi_agent_synthesis,26072.79299999999,196393,2732,71.88616398243046,22,5,1,True
|
||||
collaborative_analysis_00057,collaborative_analysis,multi_agent_synthesis,6656.256000000013,33081,7347,4.502654144548796,7,1,0,True
|
||||
collaborative_analysis_00058,collaborative_analysis,multi_agent_synthesis,5274.61199999999,58229,9303,6.259163710630979,8,2,1,True
|
||||
collaborative_analysis_00059,collaborative_analysis,multi_agent_synthesis,5612.335999999999,17516,7543,2.3221529895267135,3,0,0,True
|
||||
collaborative_analysis_00060,collaborative_analysis,multi_agent_synthesis,7323.184999999995,88159,6584,13.389884568651276,5,1,0,True
|
||||
collaborative_analysis_00061,collaborative_analysis,multi_agent_synthesis,13041.410999999982,39582,4651,8.510427864975274,5,0,0,True
|
||||
collaborative_analysis_00062,collaborative_analysis,multi_agent_synthesis,5737.938000000014,55676,4041,13.777777777777779,11,2,0,True
|
||||
collaborative_analysis_00063,collaborative_analysis,multi_agent_synthesis,13871.848999999998,111676,5758,19.39492879472039,18,5,1,True
|
||||
collaborative_analysis_00064,collaborative_analysis,multi_agent_synthesis,14159.884000000005,93620,743,126.00269179004037,11,2,0,True
|
||||
collaborative_analysis_00065,collaborative_analysis,multi_agent_synthesis,2143.2680000000064,44223,2414,18.319386909693456,5,0,0,True
|
||||
collaborative_analysis_00066,collaborative_analysis,multi_agent_synthesis,9103.234999999984,120161,2301,52.22120817036071,11,0,0,True
|
||||
collaborative_analysis_00067,collaborative_analysis,multi_agent_synthesis,7975.786999999997,51818,2211,23.43645409317051,9,2,0,True
|
||||
collaborative_analysis_00068,collaborative_analysis,multi_agent_synthesis,10306.556999999997,143550,1168,122.90239726027397,15,3,0,True
|
||||
collaborative_analysis_00069,collaborative_analysis,multi_agent_synthesis,10491.949999999975,88142,1034,85.24371373307544,13,3,0,True
|
||||
collaborative_analysis_00070,collaborative_analysis,multi_agent_synthesis,5671.043999999994,92836,4373,21.229361994054425,7,1,0,True
|
||||
collaborative_analysis_00071,collaborative_analysis,multi_agent_synthesis,2233.918000000017,35792,908,39.418502202643175,5,1,0,True
|
||||
collaborative_analysis_00072,collaborative_analysis,multi_agent_synthesis,2779.2799999999997,19132,1140,16.782456140350877,3,0,0,True
|
||||
collaborative_analysis_00073,collaborative_analysis,multi_agent_synthesis,5933.890999999989,53137,2409,22.057700290577003,7,1,0,True
|
||||
collaborative_analysis_00074,collaborative_analysis,multi_agent_synthesis,11494.603000000012,198018,8671,22.836812363049244,15,5,1,True
|
||||
collaborative_analysis_00075,collaborative_analysis,multi_agent_synthesis,3800.8010000000068,92249,1891,48.78318350079323,7,0,0,True
|
||||
collaborative_analysis_00076,collaborative_analysis,multi_agent_synthesis,15271.408000000009,110064,4836,22.759305210918114,13,4,2,True
|
||||
collaborative_analysis_00077,collaborative_analysis,multi_agent_synthesis,3524.1379999999936,49633,2359,21.03984739296312,7,0,0,True
|
||||
collaborative_analysis_00078,collaborative_analysis,multi_agent_synthesis,1085.5840000000114,34459,1481,23.267386900742743,3,0,0,True
|
||||
collaborative_analysis_00079,collaborative_analysis,multi_agent_synthesis,3396.9510000000014,7311,4899,1.492345376607471,3,0,0,True
|
||||
collaborative_analysis_00080,collaborative_analysis,multi_agent_synthesis,7375.2580000000025,40747,2612,15.599923430321592,10,3,1,True
|
||||
collaborative_analysis_00081,collaborative_analysis,multi_agent_synthesis,11392.599000000018,125175,5129,24.405342171963344,17,5,1,True
|
||||
collaborative_analysis_00082,collaborative_analysis,multi_agent_synthesis,4221.8009999999995,46903,1193,39.3151718357083,3,0,0,True
|
||||
collaborative_analysis_00083,collaborative_analysis,multi_agent_synthesis,4469.9559999999965,34392,7835,4.389534141671985,5,0,0,True
|
||||
collaborative_analysis_00084,collaborative_analysis,multi_agent_synthesis,14913.923000000012,148982,4218,35.32053105737316,17,5,2,False
|
||||
collaborative_analysis_00085,collaborative_analysis,multi_agent_synthesis,3174.0640000000158,26574,2863,9.281872162067762,3,0,0,True
|
||||
collaborative_analysis_00086,collaborative_analysis,multi_agent_synthesis,6104.687000000013,29578,2252,13.134103019538188,6,2,1,True
|
||||
collaborative_analysis_00087,collaborative_analysis,multi_agent_synthesis,3079.0619999999935,23392,7001,3.3412369661476933,3,0,0,True
|
||||
collaborative_analysis_00088,collaborative_analysis,multi_agent_synthesis,15710.582000000017,123812,1087,113.90248390064397,17,3,0,True
|
||||
collaborative_analysis_00089,collaborative_analysis,multi_agent_synthesis,9594.03499999999,123841,7467,16.585107807687155,15,3,0,True
|
||||
collaborative_analysis_00090,collaborative_analysis,multi_agent_synthesis,8018.177000000009,35223,2432,14.483141447368421,7,1,0,True
|
||||
collaborative_analysis_00091,collaborative_analysis,multi_agent_synthesis,8070.577999999983,85639,1800,47.577222222222225,9,1,0,True
|
||||
collaborative_analysis_00092,collaborative_analysis,multi_agent_synthesis,6954.7670000000035,30543,2606,11.720260936300845,8,2,1,True
|
||||
collaborative_analysis_00093,collaborative_analysis,multi_agent_synthesis,2334.4150000000072,9761,1259,7.75297855440826,3,0,0,True
|
||||
collaborative_analysis_00094,collaborative_analysis,multi_agent_synthesis,3988.2240000000024,53918,4052,13.306515301085884,7,0,0,True
|
||||
collaborative_analysis_00095,collaborative_analysis,multi_agent_synthesis,6538.421999999997,67526,4362,15.480513525905549,7,1,0,True
|
||||
collaborative_analysis_00096,collaborative_analysis,multi_agent_synthesis,7050.077000000016,89764,5545,16.188277727682596,9,0,0,True
|
||||
collaborative_analysis_00097,collaborative_analysis,multi_agent_synthesis,14613.135,138234,1905,72.56377952755905,18,4,1,True
|
||||
collaborative_analysis_00098,collaborative_analysis,multi_agent_synthesis,5859.162999999995,34186,15338,2.2288433954883295,6,2,1,True
|
||||
collaborative_analysis_00099,collaborative_analysis,multi_agent_synthesis,17759.783999999996,169187,11129,15.202354209722348,21,5,0,True
|
||||
simple_qa_00000,simple_qa,answering,855.1170000000001,3448,2896,1.1906077348066297,3,0,0,True
|
||||
simple_qa_00001,simple_qa,answering,1403.896,4962,1531,3.24101894186806,3,0,0,True
|
||||
simple_qa_00002,simple_qa,answering,1171.8220000000001,4350,787,5.527318932655654,3,0,0,True
|
||||
simple_qa_00003,simple_qa,answering,1504.4239999999998,2494,375,6.650666666666667,3,0,0,True
|
||||
simple_qa_00004,simple_qa,answering,1963.5280000000002,5963,591,10.089678510998308,5,1,0,True
|
||||
simple_qa_00005,simple_qa,answering,1452.445,5943,2101,2.8286530223703,3,0,0,True
|
||||
simple_qa_00006,simple_qa,answering,825.0729999999998,3757,1209,3.10752688172043,3,0,0,True
|
||||
simple_qa_00007,simple_qa,answering,926.895,3668,2132,1.7204502814258913,3,0,0,True
|
||||
simple_qa_00008,simple_qa,answering,1005.903,4694,1529,3.0699803793328972,3,0,0,True
|
||||
simple_qa_00009,simple_qa,answering,1038.875,5016,1632,3.073529411764706,3,0,0,True
|
||||
simple_qa_00010,simple_qa,answering,659.4789999999992,9518,859,11.080325960419092,3,0,0,True
|
||||
simple_qa_00011,simple_qa,answering,1125.273,3965,1038,3.8198458574181116,3,0,0,True
|
||||
simple_qa_00012,simple_qa,answering,1077.1380000000015,5386,1219,4.418375717801476,3,0,0,True
|
||||
simple_qa_00013,simple_qa,answering,1004.5659999999988,5660,889,6.366704161979753,3,0,0,True
|
||||
simple_qa_00014,simple_qa,answering,996.1830000000002,4420,1161,3.8070628768303187,3,0,0,True
|
||||
simple_qa_00015,simple_qa,answering,860.6720000000009,4252,1484,2.8652291105121295,3,0,0,True
|
||||
simple_qa_00016,simple_qa,answering,781.1749999999993,6704,1189,5.638351555929352,3,0,0,True
|
||||
simple_qa_00017,simple_qa,answering,700.6979999999992,4185,1526,2.7424639580602883,3,0,0,True
|
||||
simple_qa_00018,simple_qa,answering,1115.2699999999988,5439,1075,5.05953488372093,3,0,0,True
|
||||
simple_qa_00019,simple_qa,answering,850.3690000000006,3539,1636,2.16320293398533,3,0,0,True
|
||||
simple_qa_00020,simple_qa,answering,823.193999999999,5658,1063,5.322671683913453,3,0,0,True
|
||||
simple_qa_00021,simple_qa,answering,930.963000000002,6726,2009,3.3479342956694875,3,0,0,True
|
||||
simple_qa_00022,simple_qa,answering,742.083000000001,5048,1822,2.770581778265642,3,0,0,True
|
||||
simple_qa_00023,simple_qa,answering,1172.7469999999976,3674,1567,2.3446075303126994,3,0,0,True
|
||||
simple_qa_00024,simple_qa,answering,604.9790000000002,7257,1006,7.213717693836978,3,0,0,True
|
||||
simple_qa_00025,simple_qa,answering,1219.6170000000031,4464,2084,2.1420345489443378,3,0,0,True
|
||||
simple_qa_00026,simple_qa,answering,753.5990000000013,4068,1755,2.317948717948718,3,0,0,True
|
||||
simple_qa_00027,simple_qa,answering,791.2379999999998,5056,1373,3.6824471959213403,3,0,0,True
|
||||
simple_qa_00028,simple_qa,answering,827.5049999999986,3795,801,4.737827715355805,3,0,0,True
|
||||
simple_qa_00029,simple_qa,answering,677.6099999999979,4655,2300,2.023913043478261,3,0,0,True
|
||||
simple_qa_00030,simple_qa,answering,791.8140000000022,4267,720,5.926388888888889,3,0,0,True
|
||||
simple_qa_00031,simple_qa,answering,1215.0280000000002,7292,3124,2.3341869398207424,5,1,0,True
|
||||
simple_qa_00032,simple_qa,answering,1804.2910000000027,4607,2837,1.6238984843144166,3,0,0,True
|
||||
simple_qa_00033,simple_qa,answering,844.0370000000001,3221,1756,1.8342824601366743,3,0,0,True
|
||||
simple_qa_00034,simple_qa,answering,1057.2420000000022,5454,1504,3.6263297872340425,3,0,0,True
|
||||
simple_qa_00035,simple_qa,answering,1576.5220000000006,5750,1500,3.8333333333333335,3,0,0,True
|
||||
simple_qa_00036,simple_qa,answering,1026.4500000000005,7409,4583,1.616626663757364,3,0,0,True
|
||||
simple_qa_00037,simple_qa,answering,716.7670000000008,5122,1777,2.8823860438942037,3,0,0,True
|
||||
simple_qa_00038,simple_qa,answering,982.6349999999984,7826,1145,6.834934497816594,3,0,0,True
|
||||
simple_qa_00039,simple_qa,answering,701.6949999999973,5078,670,7.57910447761194,3,0,0,True
|
||||
simple_qa_00040,simple_qa,answering,1318.7110000000005,5824,2164,2.6913123844731976,3,0,0,True
|
||||
simple_qa_00041,simple_qa,answering,839.9459999999976,6330,1513,4.183740912095175,3,0,0,True
|
||||
simple_qa_00042,simple_qa,answering,1454.4789999999991,5313,1358,3.9123711340206184,3,0,0,True
|
||||
simple_qa_00043,simple_qa,answering,1366.8249999999987,5530,733,7.544338335607094,3,0,0,True
|
||||
simple_qa_00044,simple_qa,answering,1134.8300000000008,5574,919,6.065288356909685,3,0,0,True
|
||||
simple_qa_00045,simple_qa,answering,1290.6880000000028,8607,1321,6.51551854655564,5,1,0,True
|
||||
simple_qa_00046,simple_qa,answering,887.5910000000005,5342,1220,4.378688524590164,3,0,0,True
|
||||
simple_qa_00047,simple_qa,answering,1500.1400000000017,11544,1496,7.716577540106952,5,0,0,True
|
||||
simple_qa_00048,simple_qa,answering,590.2030000000025,3429,1270,2.7,3,0,0,True
|
||||
simple_qa_00049,simple_qa,answering,1328.8580000000038,3926,1557,2.5215157353885678,3,0,0,True
|
||||
simple_qa_00050,simple_qa,answering,895.7130000000006,4332,1319,3.284306292645944,3,0,0,True
|
||||
simple_qa_00051,simple_qa,answering,754.6930000000032,6203,1342,4.62220566318927,3,0,0,True
|
||||
simple_qa_00052,simple_qa,answering,1541.4049999999975,5071,1117,4.539838854073411,3,0,0,True
|
||||
simple_qa_00053,simple_qa,answering,1177.0819999999985,8016,1230,6.517073170731707,5,1,0,True
|
||||
simple_qa_00054,simple_qa,answering,498.7519999999961,5493,391,14.048593350383632,3,0,0,True
|
||||
simple_qa_00055,simple_qa,answering,1162.9900000000007,7303,1651,4.423379769836463,3,0,0,True
|
||||
simple_qa_00056,simple_qa,answering,674.510000000005,2802,669,4.188340807174888,3,0,0,True
|
||||
simple_qa_00057,simple_qa,answering,2256.7659999999987,4338,969,4.476780185758514,3,0,0,True
|
||||
simple_qa_00058,simple_qa,answering,1575.8580000000038,10725,3214,3.336963285625389,5,1,0,True
|
||||
simple_qa_00059,simple_qa,answering,1815.6789999999958,5774,1265,4.564426877470356,3,0,0,True
|
||||
simple_qa_00060,simple_qa,answering,686.0010000000045,5624,923,6.0931744312026,3,0,0,True
|
||||
simple_qa_00061,simple_qa,answering,1254.2200000000037,6000,887,6.764374295377678,3,0,0,True
|
||||
simple_qa_00062,simple_qa,answering,945.3009999999936,7475,564,13.25354609929078,3,0,0,True
|
||||
simple_qa_00063,simple_qa,answering,841.0459999999987,3683,751,4.9041278295605855,3,0,0,True
|
||||
simple_qa_00064,simple_qa,answering,1241.6660000000022,9729,904,10.76216814159292,5,1,0,True
|
||||
simple_qa_00065,simple_qa,answering,1516.855999999997,6629,1109,5.977457168620378,5,1,0,True
|
||||
simple_qa_00066,simple_qa,answering,1183.698999999997,3552,1627,2.183159188690842,3,0,0,True
|
||||
simple_qa_00067,simple_qa,answering,995.9650000000054,8377,2106,3.977682811016144,3,0,0,True
|
||||
simple_qa_00068,simple_qa,answering,959.3050000000005,4731,1465,3.2293515358361775,3,0,0,True
|
||||
simple_qa_00069,simple_qa,answering,1188.1830000000023,3612,1113,3.2452830188679247,3,0,0,True
|
||||
simple_qa_00070,simple_qa,answering,1491.27,4065,761,5.341655716162943,3,0,0,True
|
||||
simple_qa_00071,simple_qa,answering,846.0699999999974,2898,1350,2.1466666666666665,3,0,0,True
|
||||
simple_qa_00072,simple_qa,answering,1207.8729999999994,3417,747,4.57429718875502,3,0,0,True
|
||||
simple_qa_00073,simple_qa,answering,1940.8279999999963,7028,3264,2.153186274509804,5,1,0,True
|
||||
simple_qa_00074,simple_qa,answering,1482.2769999999964,5076,1081,4.695652173913044,3,0,0,True
|
||||
simple_qa_00075,simple_qa,answering,864.4090000000019,6816,897,7.59866220735786,3,0,0,True
|
||||
simple_qa_00076,simple_qa,answering,1091.8100000000024,4841,1310,3.6954198473282442,3,0,0,True
|
||||
simple_qa_00077,simple_qa,answering,1149.9900000000025,4287,737,5.8168249660786975,3,0,0,True
|
||||
simple_qa_00078,simple_qa,answering,1253.6500000000003,6102,1037,5.884281581485053,3,0,0,True
|
||||
simple_qa_00079,simple_qa,answering,2618.4089999999997,6982,680,10.26764705882353,5,1,0,True
|
||||
simple_qa_00080,simple_qa,answering,838.6209999999962,5148,824,6.247572815533981,3,0,0,True
|
||||
simple_qa_00081,simple_qa,answering,706.4880000000003,8520,643,13.250388802488336,3,0,0,True
|
||||
simple_qa_00082,simple_qa,answering,1185.3399999999965,4372,474,9.223628691983123,3,0,0,True
|
||||
simple_qa_00083,simple_qa,answering,1010.4350000000011,8796,1347,6.5300668151447665,3,0,0,True
|
||||
simple_qa_00084,simple_qa,answering,652.358999999997,3394,1270,2.6724409448818895,3,0,0,True
|
||||
simple_qa_00085,simple_qa,answering,1272.1099999999979,5066,1257,4.030230708035004,3,0,0,True
|
||||
simple_qa_00086,simple_qa,answering,1247.2220000000007,7260,610,11.901639344262295,5,1,0,True
|
||||
simple_qa_00087,simple_qa,answering,813.3010000000027,3990,2088,1.910919540229885,3,0,0,True
|
||||
simple_qa_00088,simple_qa,answering,1376.7839999999935,2576,1292,1.9938080495356036,3,0,0,True
|
||||
simple_qa_00089,simple_qa,answering,727.212999999999,5616,1291,4.350116189000775,3,0,0,True
|
||||
simple_qa_00090,simple_qa,answering,1237.8660000000039,7402,851,8.698002350176264,3,0,0,True
|
||||
simple_qa_00091,simple_qa,answering,757.8150000000007,9526,1514,6.291941875825628,5,1,0,True
|
||||
simple_qa_00092,simple_qa,answering,2362.844000000003,4959,1026,4.833333333333333,3,0,0,True
|
||||
simple_qa_00093,simple_qa,answering,1152.037,4596,920,4.995652173913044,3,0,0,True
|
||||
simple_qa_00094,simple_qa,answering,1841.4469999999951,4404,1581,2.7855787476280836,3,0,0,True
|
||||
simple_qa_00095,simple_qa,answering,1221.4370000000017,5886,1182,4.979695431472082,3,0,0,True
|
||||
simple_qa_00096,simple_qa,answering,1167.4190000000024,5641,2854,1.9765241765942536,3,0,0,True
|
||||
simple_qa_00097,simple_qa,answering,1575.9909999999948,4913,1439,3.414176511466296,3,0,0,True
|
||||
simple_qa_00098,simple_qa,answering,1244.641999999999,8507,1101,7.72661217075386,3,0,0,True
|
||||
simple_qa_00099,simple_qa,answering,1048.887999999998,4661,1839,2.5345296356715608,3,0,0,True
|
||||
tool_research_00000,tool_research,evidence_collection,2194.9050000000057,24867,3202,7.766083697688944,5,1,0,True
|
||||
tool_research_00001,tool_research,evidence_collection,3702.2710000000034,43758,1917,22.826291079812208,9,2,0,True
|
||||
tool_research_00002,tool_research,evidence_collection,4914.04399999999,29867,1906,15.669989506820567,5,1,0,True
|
||||
tool_research_00003,tool_research,evidence_collection,2975.851999999996,18814,4275,4.40093567251462,5,1,0,True
|
||||
tool_research_00004,tool_research,evidence_collection,1859.4280000000012,17926,1263,14.193190815518607,3,0,0,True
|
||||
tool_research_00005,tool_research,evidence_collection,1666.4189999999976,13686,8729,1.56787719097262,5,1,0,True
|
||||
tool_research_00006,tool_research,evidence_collection,2696.655000000007,9331,1703,5.479154433352907,3,0,0,True
|
||||
tool_research_00007,tool_research,evidence_collection,5450.783000000001,13849,1654,8.373035066505441,6,2,1,True
|
||||
tool_research_00008,tool_research,evidence_collection,1531.513000000004,17238,3296,5.22997572815534,5,1,0,True
|
||||
tool_research_00009,tool_research,evidence_collection,4081.8340000000007,13926,436,31.940366972477065,5,1,0,True
|
||||
tool_research_00010,tool_research,evidence_collection,4327.119000000011,41953,2235,18.770917225950782,5,1,0,True
|
||||
tool_research_00011,tool_research,evidence_collection,3781.2230000000113,15091,3794,3.977596204533474,5,1,0,True
|
||||
tool_research_00012,tool_research,evidence_collection,1917.4310000000078,14626,1784,8.198430493273543,3,0,0,True
|
||||
tool_research_00013,tool_research,evidence_collection,3997.425000000007,13485,1603,8.412351840299438,5,1,0,True
|
||||
tool_research_00014,tool_research,evidence_collection,2441.9809999999984,36453,2047,17.80801172447484,5,1,0,True
|
||||
tool_research_00015,tool_research,evidence_collection,3959.5280000000057,15873,1390,11.419424460431655,3,0,0,True
|
||||
tool_research_00016,tool_research,evidence_collection,1198.003,13816,976,14.155737704918034,3,0,0,True
|
||||
tool_research_00017,tool_research,evidence_collection,4552.255999999999,16333,2462,6.634037367993502,5,1,0,True
|
||||
tool_research_00018,tool_research,evidence_collection,6950.037999999992,39260,5865,6.693947144075021,6,2,1,True
|
||||
tool_research_00019,tool_research,evidence_collection,3067.522999999994,15009,2037,7.368188512518409,3,0,0,True
|
||||
tool_research_00020,tool_research,evidence_collection,4835.037999999997,30787,1662,18.524067388688326,7,1,0,True
|
||||
tool_research_00021,tool_research,evidence_collection,8310.215999999997,113647,4305,26.39883855981417,17,4,0,True
|
||||
tool_research_00022,tool_research,evidence_collection,3200.504999999993,18179,1048,17.346374045801525,5,1,0,True
|
||||
tool_research_00023,tool_research,evidence_collection,13355.828000000003,126809,1205,105.2356846473029,15,5,1,True
|
||||
tool_research_00024,tool_research,evidence_collection,3643.411999999998,21779,2025,10.755061728395061,5,1,0,True
|
||||
tool_research_00025,tool_research,evidence_collection,9670.201000000006,47663,1365,34.91794871794872,13,4,2,True
|
||||
tool_research_00026,tool_research,evidence_collection,1291.9939999999883,12623,3997,3.1581185889417065,3,0,0,True
|
||||
tool_research_00027,tool_research,evidence_collection,4673.997999999998,27499,1513,18.17514871116986,5,1,0,True
|
||||
tool_research_00028,tool_research,evidence_collection,2161.7999999999993,32414,1401,23.13633119200571,5,1,0,True
|
||||
tool_research_00029,tool_research,evidence_collection,5903.75499999999,21437,3963,5.40928589452435,5,1,0,True
|
||||
tool_research_00030,tool_research,evidence_collection,4832.2890000000025,62170,2517,24.70003972983711,9,2,0,True
|
||||
tool_research_00031,tool_research,evidence_collection,4330.880000000007,29507,2884,10.23127600554785,6,2,1,True
|
||||
tool_research_00032,tool_research,evidence_collection,1570.5789999999952,18174,849,21.406360424028268,5,1,0,True
|
||||
tool_research_00033,tool_research,evidence_collection,1797.4840000000113,34726,2226,15.600179694519317,5,1,0,True
|
||||
tool_research_00034,tool_research,evidence_collection,3040.871999999993,19123,2094,9.13228271251194,5,1,0,True
|
||||
tool_research_00035,tool_research,evidence_collection,2986.626000000001,24572,1303,18.858019953952418,5,1,0,True
|
||||
tool_research_00036,tool_research,evidence_collection,3130.6490000000053,28061,1577,17.793912492073556,3,0,0,True
|
||||
tool_research_00037,tool_research,evidence_collection,3123.7370000000055,22728,3665,6.201364256480218,5,1,0,True
|
||||
tool_research_00038,tool_research,evidence_collection,1708.3070000000048,29910,1078,27.74582560296846,5,1,0,True
|
||||
tool_research_00039,tool_research,evidence_collection,4255.195999999998,21270,1412,15.063739376770538,5,1,0,True
|
||||
tool_research_00040,tool_research,evidence_collection,2188.941,24341,4087,5.955713237093223,5,1,0,True
|
||||
tool_research_00041,tool_research,evidence_collection,2437.484999999995,4248,1853,2.2924986508364813,3,0,0,True
|
||||
tool_research_00042,tool_research,evidence_collection,2187.698999999995,8817,2395,3.681419624217119,3,0,0,True
|
||||
tool_research_00043,tool_research,evidence_collection,5124.787999999995,36771,2156,17.055194805194805,9,2,0,True
|
||||
tool_research_00044,tool_research,evidence_collection,2136.277000000007,23014,3951,5.824854467223488,5,1,0,True
|
||||
tool_research_00045,tool_research,evidence_collection,2712.2329999999974,13715,4904,2.7966965742251224,5,1,0,True
|
||||
tool_research_00046,tool_research,evidence_collection,2093.755999999999,27149,2497,10.872647176611935,3,0,0,True
|
||||
tool_research_00047,tool_research,evidence_collection,3331.8359999999957,10694,2450,4.364897959183674,3,0,0,True
|
||||
tool_research_00048,tool_research,evidence_collection,2496.739000000005,23797,420,56.65952380952381,5,1,0,True
|
||||
tool_research_00049,tool_research,evidence_collection,3162.072999999992,37174,6914,5.376627133352618,5,1,0,True
|
||||
tool_research_00050,tool_research,evidence_collection,3349.9610000000075,20453,1503,13.608117099135063,5,1,0,True
|
||||
tool_research_00051,tool_research,evidence_collection,2585.735999999997,20752,4970,4.175452716297786,5,1,0,True
|
||||
tool_research_00052,tool_research,evidence_collection,2241.700999999992,18226,1014,17.974358974358974,5,1,0,True
|
||||
tool_research_00053,tool_research,evidence_collection,1681.621000000007,20527,1964,10.451629327902241,5,1,0,True
|
||||
tool_research_00054,tool_research,evidence_collection,4616.5809999999965,14793,1020,14.50294117647059,5,1,0,True
|
||||
tool_research_00055,tool_research,evidence_collection,1986.9599999999964,36674,1499,24.46564376250834,5,1,0,True
|
||||
tool_research_00056,tool_research,evidence_collection,3329.991000000007,21611,2138,10.108044901777362,5,1,0,True
|
||||
tool_research_00057,tool_research,evidence_collection,1935.023000000001,11508,3856,2.9844398340248963,3,0,0,True
|
||||
tool_research_00058,tool_research,evidence_collection,2901.527999999999,31197,1663,18.759470835838844,5,1,0,True
|
||||
tool_research_00059,tool_research,evidence_collection,3321.638000000007,11370,816,13.933823529411764,3,0,0,True
|
||||
tool_research_00060,tool_research,evidence_collection,3683.4269999999947,22492,1908,11.78825995807128,5,1,0,True
|
||||
tool_research_00061,tool_research,evidence_collection,2848.731999999998,18988,1760,10.788636363636364,5,1,0,True
|
||||
tool_research_00062,tool_research,evidence_collection,2672.6560000000036,11461,1837,6.238976592270006,5,1,0,True
|
||||
tool_research_00063,tool_research,evidence_collection,2669.6290000000004,12186,2987,4.079678607298293,3,0,0,True
|
||||
tool_research_00064,tool_research,evidence_collection,1733.4749999999985,20624,2281,9.041648399824638,5,1,0,True
|
||||
tool_research_00065,tool_research,evidence_collection,1969.7800000000002,37289,2064,18.066375968992247,5,1,0,True
|
||||
tool_research_00066,tool_research,evidence_collection,2515.674000000004,27763,948,29.285864978902953,5,1,0,True
|
||||
tool_research_00067,tool_research,evidence_collection,3096.862999999999,25812,1096,23.55109489051095,5,1,0,True
|
||||
tool_research_00068,tool_research,evidence_collection,2049.244999999999,27451,1646,16.677399756986635,5,1,0,True
|
||||
tool_research_00069,tool_research,evidence_collection,1731.0909999999922,25997,2954,8.800609343263371,5,1,0,True
|
||||
tool_research_00070,tool_research,evidence_collection,3312.636999999995,31567,3135,10.069218500797447,5,1,0,True
|
||||
tool_research_00071,tool_research,evidence_collection,1862.328000000005,20908,2780,7.520863309352518,5,1,0,True
|
||||
tool_research_00072,tool_research,evidence_collection,3047.896000000009,54132,1025,52.81170731707317,5,1,0,True
|
||||
tool_research_00073,tool_research,evidence_collection,2561.8630000000026,21435,4790,4.474947807933194,5,1,0,True
|
||||
tool_research_00074,tool_research,evidence_collection,4560.357999999994,79773,2385,33.44779874213837,13,3,0,True
|
||||
tool_research_00075,tool_research,evidence_collection,3243.395000000007,7843,2993,2.6204477113264284,3,0,0,True
|
||||
tool_research_00076,tool_research,evidence_collection,2738.9289999999987,23031,2795,8.240071556350626,5,1,0,True
|
||||
tool_research_00077,tool_research,evidence_collection,5143.501999999998,26921,3689,7.297641637300082,3,0,0,True
|
||||
tool_research_00078,tool_research,evidence_collection,2541.331999999997,10770,5383,2.000743080066877,3,0,0,True
|
||||
tool_research_00079,tool_research,evidence_collection,4596.682000000002,30560,3128,9.769820971867007,9,2,0,True
|
||||
tool_research_00080,tool_research,evidence_collection,2516.4350000000013,10007,1693,5.910809214412286,3,0,0,True
|
||||
tool_research_00081,tool_research,evidence_collection,3084.7260000000033,17944,830,21.619277108433735,5,1,0,True
|
||||
tool_research_00082,tool_research,evidence_collection,2914.749999999998,25400,982,25.865580448065174,5,1,0,True
|
||||
tool_research_00083,tool_research,evidence_collection,2230.4889999999914,24604,2144,11.475746268656716,5,1,0,True
|
||||
tool_research_00084,tool_research,evidence_collection,3443.204000000009,24850,739,33.62652232746955,5,1,0,True
|
||||
tool_research_00085,tool_research,evidence_collection,5764.497000000006,31697,6531,4.853314959424284,6,2,1,True
|
||||
tool_research_00086,tool_research,evidence_collection,2663.731999999996,14968,967,15.478800413650465,5,1,0,True
|
||||
tool_research_00087,tool_research,evidence_collection,1660.2049999999906,10680,3250,3.286153846153846,5,1,0,True
|
||||
tool_research_00088,tool_research,evidence_collection,1999.1580000000085,11601,3306,3.5090744101633393,3,0,0,True
|
||||
tool_research_00089,tool_research,evidence_collection,2695.4450000000065,10711,3265,3.280551301684533,5,1,0,True
|
||||
tool_research_00090,tool_research,evidence_collection,5276.9389999999985,15851,1980,8.005555555555556,5,1,0,True
|
||||
tool_research_00091,tool_research,evidence_collection,5764.26699999999,27062,2151,12.581125058112505,6,2,1,True
|
||||
tool_research_00092,tool_research,evidence_collection,1482.0979999999936,17916,936,19.141025641025642,5,1,0,True
|
||||
tool_research_00093,tool_research,evidence_collection,2160.2140000000104,36749,2052,17.908869395711502,5,1,0,True
|
||||
tool_research_00094,tool_research,evidence_collection,3420.692000000017,15674,8252,1.8994183228308288,3,0,0,True
|
||||
tool_research_00095,tool_research,evidence_collection,1882.05099999999,19776,2123,9.315120113047573,5,1,0,True
|
||||
tool_research_00096,tool_research,evidence_collection,3586.549000000005,36710,1309,28.044308632543927,5,1,0,True
|
||||
tool_research_00097,tool_research,evidence_collection,1987.364999999997,14435,3124,4.62067861715749,5,1,0,True
|
||||
tool_research_00098,tool_research,evidence_collection,3917.211000000009,16232,1378,11.779390420899855,6,2,1,True
|
||||
tool_research_00099,tool_research,evidence_collection,4009.145999999987,74407,2235,33.2917225950783,5,1,0,True
|
||||
|
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
Binary file not shown.
|
After Width: | Height: | Size: 46 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 112 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 82 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 145 KiB |
@@ -0,0 +1,183 @@
|
||||
{
|
||||
"global": {
|
||||
"transition_probabilities": {
|
||||
"CallTool->Think": 0.9891472868217054,
|
||||
"Idle->Think": 0.9911167512690355,
|
||||
"Retry->CallTool": 0.9176470588235294,
|
||||
"Think->CallAgent": 0.12293086660175268,
|
||||
"Think->CallTool": 0.15603700097370984,
|
||||
"Think->Failed": 0.0017039922103213243,
|
||||
"Think->Send": 0.5148490749756572,
|
||||
"Think->Split": 0.20374878286270692,
|
||||
"Wait->Failed": 0.36363636363636365
|
||||
},
|
||||
"duration_ms": {
|
||||
"mean": 285.679917634447,
|
||||
"std": 550.6643665581886,
|
||||
"cv": 1.9275571454862042,
|
||||
"p50": 8.0,
|
||||
"p95": 1323.2897999999977,
|
||||
"count": 5597
|
||||
},
|
||||
"message_size_bytes": {
|
||||
"mean": 5570.409505092013,
|
||||
"std": 6586.248171004335,
|
||||
"cv": 1.1823633729232519,
|
||||
"p50": 3158.0,
|
||||
"p95": 18393.199999999997,
|
||||
"count": 5597
|
||||
}
|
||||
},
|
||||
"task_types": {
|
||||
"collaborative_analysis": {
|
||||
"phase": "multi_agent_synthesis",
|
||||
"task_count": 260,
|
||||
"tool_probability": 0.4806201550387597,
|
||||
"split_probability": 0.8192307692307692,
|
||||
"mean_subtasks": 2.976923076923077,
|
||||
"retry_probability": 0.12470588235294118,
|
||||
"mean_retries_if_any": 1.1627906976744187,
|
||||
"failure_probability": 0.007692307692307693,
|
||||
"think_time_ms": {
|
||||
"mean": 1012.4040078828829,
|
||||
"std": 819.189229985454,
|
||||
"cv": 0.8091524960460444,
|
||||
"p50": 802.0150000000001,
|
||||
"p95": 2609.3335999999995,
|
||||
"count": 888
|
||||
},
|
||||
"external_size_bytes": {
|
||||
"mean": 4103.692307692308,
|
||||
"std": 3820.340621837784,
|
||||
"cv": 0.9309520147688984,
|
||||
"p50": 3039.5,
|
||||
"p95": 11107.699999999995,
|
||||
"count": 260
|
||||
},
|
||||
"request_size_bytes": {
|
||||
"mean": 3936.623019182652,
|
||||
"std": 3891.679972776879,
|
||||
"cv": 0.9885833501997089,
|
||||
"p50": 2796.0,
|
||||
"p95": 10800.3,
|
||||
"count": 1199
|
||||
},
|
||||
"response_size_bytes": {
|
||||
"mean": 11829.127142857144,
|
||||
"std": 8952.816088861513,
|
||||
"cv": 0.7568450301312002,
|
||||
"p50": 9558.5,
|
||||
"p95": 29122.249999999993,
|
||||
"count": 1400
|
||||
},
|
||||
"message_count_per_task": {
|
||||
"mean": 11.01923076923077,
|
||||
"std": 5.376910696585285,
|
||||
"cv": 0.48795699166218987,
|
||||
"p50": 10.0,
|
||||
"p95": 21.049999999999983,
|
||||
"count": 260
|
||||
}
|
||||
},
|
||||
"simple_qa": {
|
||||
"phase": "answering",
|
||||
"task_count": 260,
|
||||
"tool_probability": 0.13740458015267176,
|
||||
"split_probability": 0.03461538461538462,
|
||||
"mean_subtasks": 1.0076923076923077,
|
||||
"retry_probability": 0.02702702702702703,
|
||||
"mean_retries_if_any": 1.0,
|
||||
"failure_probability": 0.0,
|
||||
"think_time_ms": {
|
||||
"mean": 315.74304316546767,
|
||||
"std": 193.59344702605458,
|
||||
"cv": 0.6131360649634342,
|
||||
"p50": 262.062,
|
||||
"p95": 693.3605,
|
||||
"count": 556
|
||||
},
|
||||
"external_size_bytes": {
|
||||
"mean": 1285.7846153846153,
|
||||
"std": 562.841233039538,
|
||||
"cv": 0.43774145864327046,
|
||||
"p50": 1167.5,
|
||||
"p95": 2332.1,
|
||||
"count": 260
|
||||
},
|
||||
"request_size_bytes": {
|
||||
"mean": 1646.314381270903,
|
||||
"std": 819.0778288985601,
|
||||
"cv": 0.4975221247027301,
|
||||
"p50": 1537.0,
|
||||
"p95": 3065.4999999999995,
|
||||
"count": 299
|
||||
},
|
||||
"response_size_bytes": {
|
||||
"mean": 1909.388888888889,
|
||||
"std": 1208.6473367395993,
|
||||
"cv": 0.6330021839830309,
|
||||
"p50": 1577.5,
|
||||
"p95": 4346.099999999999,
|
||||
"count": 558
|
||||
},
|
||||
"message_count_per_task": {
|
||||
"mean": 4.296153846153846,
|
||||
"std": 0.7184281823915581,
|
||||
"cv": 0.16722589742328123,
|
||||
"p50": 4.0,
|
||||
"p95": 6.0,
|
||||
"count": 260
|
||||
}
|
||||
},
|
||||
"tool_research": {
|
||||
"phase": "evidence_collection",
|
||||
"task_count": 260,
|
||||
"tool_probability": 0.7631578947368421,
|
||||
"split_probability": 0.2076923076923077,
|
||||
"mean_subtasks": 1.1692307692307693,
|
||||
"retry_probability": 0.09019607843137255,
|
||||
"mean_retries_if_any": 1.0952380952380953,
|
||||
"failure_probability": 0.0038461538461538464,
|
||||
"think_time_ms": {
|
||||
"mean": 660.7411426666666,
|
||||
"std": 548.0475005635645,
|
||||
"cv": 0.8294435826286146,
|
||||
"p50": 513.7415,
|
||||
"p95": 1615.4994999999997,
|
||||
"count": 750
|
||||
},
|
||||
"external_size_bytes": {
|
||||
"mean": 2591.223076923077,
|
||||
"std": 1938.9205968801086,
|
||||
"cv": 0.7482646377101818,
|
||||
"p50": 2023.0,
|
||||
"p95": 6498.299999999999,
|
||||
"count": 260
|
||||
},
|
||||
"request_size_bytes": {
|
||||
"mean": 2178.8425760286227,
|
||||
"std": 1869.411620553448,
|
||||
"cv": 0.8579837942954215,
|
||||
"p50": 1586.0,
|
||||
"p95": 6085.500000000001,
|
||||
"count": 559
|
||||
},
|
||||
"response_size_bytes": {
|
||||
"mean": 6327.029003783102,
|
||||
"std": 4973.701881543845,
|
||||
"cv": 0.7861038535732859,
|
||||
"p50": 4987.0,
|
||||
"p95": 15569.8,
|
||||
"count": 793
|
||||
},
|
||||
"message_count_per_task": {
|
||||
"mean": 6.211538461538462,
|
||||
"std": 2.097035805988451,
|
||||
"cv": 0.33760328765139147,
|
||||
"p50": 6.0,
|
||||
"p95": 11.0,
|
||||
"count": 260
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,26 @@
|
||||
timeout_probability,max_retries,success_rate,mean_retries,mean_amplification,mean_latency_ms
|
||||
0.0,0,1.0,0.0,9.014727352307537,1829.8204232372348
|
||||
0.0,1,1.0,0.0,9.017931822157774,1786.1398565415025
|
||||
0.0,2,1.0,0.0,9.497944538818517,1655.013246029438
|
||||
0.0,3,1.0,0.0,8.981130309004985,1716.8465797602803
|
||||
0.0,5,1.0,0.0,9.540066677486474,1716.7430554392593
|
||||
0.03,0,0.9666666666666667,0.0,9.063950194066456,1669.7925665017842
|
||||
0.03,1,0.9958333333333333,0.016666666666666666,9.063781276545864,1657.0420076151597
|
||||
0.03,2,1.0,0.016666666666666666,9.014566351856745,1691.3863870856096
|
||||
0.03,3,1.0,0.020833333333333332,9.637237082920953,1721.830506046892
|
||||
0.03,5,1.0,0.0125,9.649347558637414,1718.5997383083138
|
||||
0.08,0,0.9041666666666667,0.0,8.25627307377185,1635.0229558657152
|
||||
0.08,1,1.0,0.05416666666666667,9.289215941037927,1787.9821751080794
|
||||
0.08,2,1.0,0.06666666666666667,9.431797013914702,1916.4375526605215
|
||||
0.08,3,1.0,0.058333333333333334,9.050271941109205,1898.8272546658047
|
||||
0.08,5,1.0,0.07916666666666666,9.741006123762736,1970.2545335768014
|
||||
0.15,0,0.8416666666666667,0.0,8.164931539209656,1610.0725491672833
|
||||
0.15,1,0.9833333333333333,0.10833333333333334,9.088215821284614,1938.8382504596384
|
||||
0.15,2,1.0,0.1,9.261076832398844,1941.657277871303
|
||||
0.15,3,0.9958333333333333,0.13333333333333333,11.372866350773522,2027.2488180006546
|
||||
0.15,5,1.0,0.13333333333333333,8.152159646681561,2064.0974036821353
|
||||
0.25,0,0.7916666666666666,0.0,7.82021056651408,1652.063945123461
|
||||
0.25,1,0.9541666666666667,0.17916666666666667,8.424662742312817,2194.736913880946
|
||||
0.25,2,0.9916666666666667,0.2875,9.275168718803195,2475.475754982108
|
||||
0.25,3,1.0,0.2833333333333333,8.808713566195896,2429.5919980366966
|
||||
0.25,5,1.0,0.1875,9.459047702518982,2044.5400456955706
|
||||
|
@@ -0,0 +1,9 @@
|
||||
arrival_rate,offered_tasks,completed_tasks,throughput_per_second,mean_delay_ms,p95_delay_ms,queue_peak,drop_rate,success_rate,mean_amplification
|
||||
0.5,87,79,0.49375,5690.601711699437,12756.456777674,2,0.0,1.0,32.68982726898488
|
||||
1.0,178,154,0.9625,28654.713037581158,50223.56851458479,35,0.0,1.0,35.61819225706701
|
||||
2.0,354,315,1.96875,159265.0479860076,259462.94208402873,216,0.0,1.0,27.685762197623816
|
||||
4.0,735,553,3.45625,360462.8938916123,611043.0735286651,500,0.1251700680272109,0.9981916817359855,28.819579849617657
|
||||
6.0,1140,538,3.3625,406978.074020204,627164.1820327837,500,0.4280701754385965,1.0,30.664346517813648
|
||||
8.0,1419,478,2.9875,439078.312694735,605565.2288237411,500,0.5419309372797745,0.997907949790795,28.477068296105013
|
||||
10.0,1736,459,2.86875,462378.903316947,623226.2655493785,500,0.6215437788018433,0.9978213507625272,29.655131218317656
|
||||
12.0,2196,407,2.54375,503595.3336070842,641094.366587491,500,0.7108378870673953,1.0,29.595658555137497
|
||||
|
@@ -0,0 +1,18 @@
|
||||
{
|
||||
"best_model_by_internal_bytes_mape": {
|
||||
"model": "full_model",
|
||||
"metric": "internal_bytes",
|
||||
"mae": 9852.85421644164,
|
||||
"rmse": 11957.784318614104,
|
||||
"mape_percent": 27.25831155178904
|
||||
},
|
||||
"best_model_by_latency_mape": {
|
||||
"model": "full_model",
|
||||
"metric": "latency_ms",
|
||||
"mae": 1677.2186263904505,
|
||||
"rmse": 2068.228406399321,
|
||||
"mape_percent": 38.01609858429338
|
||||
},
|
||||
"max_stress_arrival_rate": 12.0,
|
||||
"max_observed_p95_delay_ms": 641094.366587491
|
||||
}
|
||||
@@ -0,0 +1,16 @@
|
||||
model,metric,mae,rmse,mape_percent
|
||||
full_model,internal_bytes,9852.85421644164,11957.784318614104,27.25831155178904
|
||||
full_model,latency_ms,1677.2186263904505,2068.228406399321,38.01609858429338
|
||||
full_model,message_count,0.43277777777777793,0.5471686380984558,5.855207621776822
|
||||
full_model,tool_calls,0.11166666666666662,0.14041275134666625,14.427527090058401
|
||||
full_model,amplification,4.305062499013978,5.243570352907988,22.67666226433828
|
||||
no_context,internal_bytes,28387.670805477606,38228.5095522755,119.54177279524332
|
||||
no_context,latency_ms,2907.231795727213,3869.904048337353,62.66674153347929
|
||||
no_context,message_count,2.485555555555556,3.1931712438565825,38.768826743972944
|
||||
no_context,tool_calls,0.6505555555555556,0.7056603159321639,196.9584307828373
|
||||
no_context,amplification,10.922275115304535,13.789521598016519,70.65863904754978
|
||||
static_mean,internal_bytes,29834.93333333333,32709.783175317236,230.39064998346973
|
||||
static_mean,latency_ms,2757.6886622222223,3058.6901465213614,119.58343818448623
|
||||
static_mean,message_count,2.5155555555555558,2.7855500155066126,48.03496553983882
|
||||
static_mean,tool_calls,0.5444444444444444,0.6355225321645873,264.95059144468667
|
||||
static_mean,amplification,10.71876769134868,12.026846682885607,111.10365289444462
|
||||
|
@@ -0,0 +1,10 @@
|
||||
task_type,model,actual_internal_bytes,predicted_internal_bytes,actual_latency_ms,predicted_latency_ms,actual_message_count,predicted_message_count,actual_tool_calls,predicted_tool_calls,actual_amplification,predicted_amplification
|
||||
collaborative_analysis,static_mean,82782.45,38030.049999999996,8428.771760000001,4292.238766666668,9.88,6.1066666666666665,1.66,0.9266666666666667,33.798140646040636,17.719989109017618
|
||||
collaborative_analysis,no_context,82782.45,18429.737056529975,8428.771760000001,1933.7549094389146,9.88,4.658333333333333,1.66,0.6333333333333333,33.798140646040636,10.99100144733211
|
||||
collaborative_analysis,full_model,82782.45,65408.811967296744,8428.771760000001,5132.429177599434,9.88,9.033333333333333,1.66,1.4333333333333333,33.798140646040636,25.68477275651994
|
||||
simple_qa,static_mean,5514.23,38030.049999999996,1128.43623,4292.238766666668,3.24,6.1066666666666665,0.11,0.9266666666666667,4.875984197964249,17.719989109017618
|
||||
simple_qa,no_context,5514.23,19556.05971301258,1128.43623,1878.3339705388123,3.24,5.0,0.11,0.65,4.875984197964249,10.442958092513376
|
||||
simple_qa,full_model,5514.23,4564.059252059445,1128.43623,740.9752102854878,3.24,3.2666666666666666,0.11,0.13333333333333333,4.875984197964249,4.07657616682107
|
||||
tool_research,static_mean,25793.47,38030.049999999996,3319.5083100000024,4292.238766666668,5.2,6.1066666666666665,1.01,0.9266666666666667,14.485842483047964,17.719989109017618
|
||||
tool_research,no_context,25793.47,19025.000240049787,3319.5083100000024,1842.727513918263,5.2,4.725,1.01,0.625,14.485842483047964,10.09313023039201
|
||||
tool_research,full_model,25793.47,14558.716131318892,3319.5083100000024,1971.65603294373,5.2,4.775,1.01,0.925,14.485842483047964,10.483430906669906
|
||||
|
@@ -0,0 +1,6 @@
|
||||
numpy>=1.20
|
||||
pandas>=1.2
|
||||
matplotlib>=3.3
|
||||
PyYAML>=5.4
|
||||
requests>=2.25
|
||||
|
||||
@@ -0,0 +1,11 @@
|
||||
$ErrorActionPreference = 'Stop'
|
||||
$scriptDir = Split-Path -Parent $MyInvocation.MyCommand.Path
|
||||
Set-Location $scriptDir
|
||||
|
||||
if (-not $env:OPENAI_API_KEY) {
|
||||
throw '请先设置 OPENAI_API_KEY。也可以直接运行 run_local.ps1 使用本地画像。'
|
||||
}
|
||||
if (-not $env:OPENAI_MODEL) {
|
||||
throw '请先设置 OPENAI_MODEL。'
|
||||
}
|
||||
python run_pipeline.py --generator llm
|
||||
@@ -0,0 +1,4 @@
|
||||
$ErrorActionPreference = 'Stop'
|
||||
$scriptDir = Split-Path -Parent $MyInvocation.MyCommand.Path
|
||||
Set-Location $scriptDir
|
||||
python run_pipeline.py
|
||||
@@ -0,0 +1,77 @@
|
||||
import argparse
|
||||
import shutil
|
||||
from pathlib import Path
|
||||
|
||||
import pandas as pd
|
||||
|
||||
from src.common import ensure_dirs, load_config, load_json, save_json, seeded_rng
|
||||
from src.data_generator import aggregate_task_truth, generate_event_log, generate_profiles
|
||||
from src.experiments import make_figures, retry_experiment, stress_experiment, validation_experiment
|
||||
from src.parameter_estimation import estimate_parameters
|
||||
|
||||
|
||||
def parse_args():
|
||||
parser = argparse.ArgumentParser(description="Agent network traffic data generation and experiments")
|
||||
parser.add_argument("--config", default="configs/default.yaml")
|
||||
parser.add_argument("--output", default="outputs/latest")
|
||||
parser.add_argument("--generator", choices=["local", "llm"], default="local")
|
||||
parser.add_argument("--steps", default="generate,estimate,experiment")
|
||||
parser.add_argument("--no-fallback", action="store_true")
|
||||
return parser.parse_args()
|
||||
|
||||
|
||||
def main():
|
||||
args = parse_args()
|
||||
root = Path(__file__).resolve().parent
|
||||
config_path = (root / args.config).resolve() if not Path(args.config).is_absolute() else Path(args.config)
|
||||
output_path = (root / args.output).resolve() if not Path(args.output).is_absolute() else Path(args.output)
|
||||
cfg = load_config(config_path)
|
||||
dirs = ensure_dirs(output_path)
|
||||
shutil.copy2(config_path, output_path / "config_used.yaml")
|
||||
steps = {x.strip() for x in args.steps.split(",") if x.strip()}
|
||||
rng = seeded_rng(int(cfg["seed"]))
|
||||
|
||||
if "generate" in steps:
|
||||
profiles, metadata = generate_profiles(
|
||||
args.generator, cfg["generation"]["task_types"], cfg["generation"]["llm"],
|
||||
allow_fallback=not args.no_fallback,
|
||||
)
|
||||
save_json({"metadata": metadata, "profiles": profiles}, dirs["data"] / "behavior_profiles.json")
|
||||
train = generate_event_log(profiles, int(cfg["generation"]["train_tasks_per_type"]), rng, cfg["network"])
|
||||
test = generate_event_log(profiles, int(cfg["generation"]["test_tasks_per_type"]), rng, cfg["network"])
|
||||
train.to_csv(dirs["data"] / "train_events.csv", index=False, encoding="utf-8-sig")
|
||||
test.to_csv(dirs["data"] / "test_events.csv", index=False, encoding="utf-8-sig")
|
||||
aggregate_task_truth(test).to_csv(dirs["data"] / "task_truth.csv", index=False, encoding="utf-8-sig")
|
||||
print("[generate] profiles=%d, train_events=%d, test_events=%d" % (len(profiles), len(train), len(test)))
|
||||
|
||||
if "estimate" in steps:
|
||||
train = pd.read_csv(dirs["data"] / "train_events.csv")
|
||||
params = estimate_parameters(train)
|
||||
save_json(params, dirs["parameters"] / "estimated_parameters.json")
|
||||
print("[estimate] task_types=%s" % ",".join(params["task_types"].keys()))
|
||||
|
||||
if "experiment" in steps:
|
||||
params = load_json(dirs["parameters"] / "estimated_parameters.json")
|
||||
truth = pd.read_csv(dirs["data"] / "task_truth.csv")
|
||||
predictions, metrics = validation_experiment(truth, params, cfg, rng)
|
||||
stress = stress_experiment(params, cfg, rng)
|
||||
retry = retry_experiment(params, cfg, rng)
|
||||
predictions.to_csv(dirs["results"] / "validation_predictions.csv", index=False, encoding="utf-8-sig")
|
||||
metrics.to_csv(dirs["results"] / "validation_metrics.csv", index=False, encoding="utf-8-sig")
|
||||
stress.to_csv(dirs["results"] / "stress_results.csv", index=False, encoding="utf-8-sig")
|
||||
retry.to_csv(dirs["results"] / "retry_results.csv", index=False, encoding="utf-8-sig")
|
||||
make_figures(predictions, metrics, stress, retry, dirs["figures"])
|
||||
summary = {
|
||||
"best_model_by_internal_bytes_mape": metrics[metrics["metric"] == "internal_bytes"].sort_values("mape_percent").iloc[0].to_dict(),
|
||||
"best_model_by_latency_mape": metrics[metrics["metric"] == "latency_ms"].sort_values("mape_percent").iloc[0].to_dict(),
|
||||
"max_stress_arrival_rate": float(stress["arrival_rate"].max()),
|
||||
"max_observed_p95_delay_ms": float(stress["p95_delay_ms"].max()),
|
||||
}
|
||||
save_json(summary, dirs["results"] / "summary.json")
|
||||
print("[experiment] results written to %s" % output_path)
|
||||
print(metrics[metrics["metric"].isin(["internal_bytes", "latency_ms"])][["model", "metric", "mape_percent"]].to_string(index=False))
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
|
||||
@@ -0,0 +1,2 @@
|
||||
"""Agent traffic modeling experiment package."""
|
||||
|
||||
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
@@ -0,0 +1,61 @@
|
||||
import json
|
||||
import math
|
||||
import os
|
||||
import random
|
||||
from pathlib import Path
|
||||
|
||||
import numpy as np
|
||||
import yaml
|
||||
|
||||
|
||||
def load_config(path):
|
||||
with open(path, "r", encoding="utf-8") as f:
|
||||
return yaml.safe_load(f)
|
||||
|
||||
|
||||
def ensure_dirs(root):
|
||||
root = Path(root)
|
||||
dirs = {name: root / name for name in ("data", "parameters", "results", "figures")}
|
||||
for directory in dirs.values():
|
||||
directory.mkdir(parents=True, exist_ok=True)
|
||||
return dirs
|
||||
|
||||
|
||||
def save_json(data, path):
|
||||
with open(path, "w", encoding="utf-8") as f:
|
||||
json.dump(data, f, ensure_ascii=False, indent=2)
|
||||
|
||||
|
||||
def load_json(path):
|
||||
with open(path, "r", encoding="utf-8") as f:
|
||||
return json.load(f)
|
||||
|
||||
|
||||
def seeded_rng(seed):
|
||||
random.seed(seed)
|
||||
np.random.seed(seed)
|
||||
return np.random.default_rng(seed)
|
||||
|
||||
|
||||
def clamp(value, low, high):
|
||||
return max(low, min(high, value))
|
||||
|
||||
|
||||
def lognormal_params_from_mean_cv(mean, cv):
|
||||
mean = max(float(mean), 1e-6)
|
||||
cv = max(float(cv), 1e-6)
|
||||
sigma2 = math.log(cv * cv + 1.0)
|
||||
sigma = math.sqrt(sigma2)
|
||||
mu = math.log(mean) - sigma2 / 2.0
|
||||
return mu, sigma
|
||||
|
||||
|
||||
def sample_lognormal(rng, mean, cv, minimum=1.0):
|
||||
mu, sigma = lognormal_params_from_mean_cv(mean, cv)
|
||||
return max(minimum, float(rng.lognormal(mu, sigma)))
|
||||
|
||||
|
||||
def env(name, default=None):
|
||||
value = os.environ.get(name)
|
||||
return default if value in (None, "") else value
|
||||
|
||||
@@ -0,0 +1,308 @@
|
||||
import json
|
||||
import re
|
||||
import uuid
|
||||
from copy import deepcopy
|
||||
|
||||
import pandas as pd
|
||||
import requests
|
||||
|
||||
from .common import clamp, sample_lognormal
|
||||
|
||||
|
||||
DEFAULT_PROFILES = [
|
||||
{
|
||||
"task_type": "simple_qa",
|
||||
"description": "单节点即可完成的简短问答，少量情况下调用工具。",
|
||||
"phase": "answering",
|
||||
"tool_probability": 0.10,
|
||||
"split_probability": 0.05,
|
||||
"mean_subtasks": 1.2,
|
||||
"timeout_probability": 0.02,
|
||||
"failure_probability": 0.01,
|
||||
"think_time_ms_mean": 420,
|
||||
"think_time_cv": 0.55,
|
||||
"request_size_bytes_mean": 1800,
|
||||
"response_size_bytes_mean": 2600,
|
||||
"message_size_cv": 0.45,
|
||||
},
|
||||
{
|
||||
"task_type": "tool_research",
|
||||
"description": "需要搜索、数据库或工具结果的研究任务。",
|
||||
"phase": "evidence_collection",
|
||||
"tool_probability": 0.78,
|
||||
"split_probability": 0.20,
|
||||
"mean_subtasks": 1.8,
|
||||
"timeout_probability": 0.07,
|
||||
"failure_probability": 0.025,
|
||||
"think_time_ms_mean": 900,
|
||||
"think_time_cv": 0.75,
|
||||
"request_size_bytes_mean": 3200,
|
||||
"response_size_bytes_mean": 8500,
|
||||
"message_size_cv": 0.70,
|
||||
},
|
||||
{
|
||||
"task_type": "collaborative_analysis",
|
||||
"description": "协调多个执行 Agent 并汇总结果的复杂分析任务。",
|
||||
"phase": "multi_agent_synthesis",
|
||||
"tool_probability": 0.48,
|
||||
"split_probability": 0.82,
|
||||
"mean_subtasks": 3.4,
|
||||
"timeout_probability": 0.09,
|
||||
"failure_probability": 0.035,
|
||||
"think_time_ms_mean": 1450,
|
||||
"think_time_cv": 0.85,
|
||||
"request_size_bytes_mean": 5200,
|
||||
"response_size_bytes_mean": 11800,
|
||||
"message_size_cv": 0.80,
|
||||
},
|
||||
]
|
||||
|
||||
|
||||
PROFILE_KEYS = {
|
||||
"task_type", "description", "phase", "tool_probability", "split_probability",
|
||||
"mean_subtasks", "timeout_probability", "failure_probability",
|
||||
"think_time_ms_mean", "think_time_cv", "request_size_bytes_mean",
|
||||
"response_size_bytes_mean", "message_size_cv",
|
||||
}
|
||||
|
||||
|
||||
def _extract_json(text):
|
||||
text = text.strip()
|
||||
fenced = re.search(r"```(?:json)?\s*(.*?)```", text, flags=re.S | re.I)
|
||||
if fenced:
|
||||
text = fenced.group(1).strip()
|
||||
start = min([i for i in (text.find("["), text.find("{")) if i >= 0] or [0])
|
||||
text = text[start:]
|
||||
if text.startswith("{"):
|
||||
obj = json.loads(text)
|
||||
return obj.get("profiles", obj)
|
||||
return json.loads(text)
|
||||
|
||||
|
||||
def _validate_profiles(profiles, requested_types):
|
||||
if not isinstance(profiles, list):
|
||||
raise ValueError("LLM output must be a JSON list")
|
||||
validated = []
|
||||
by_type = {p["task_type"]: p for p in DEFAULT_PROFILES}
|
||||
for raw in profiles:
|
||||
if not isinstance(raw, dict) or "task_type" not in raw:
|
||||
continue
|
||||
base = deepcopy(by_type.get(raw["task_type"], DEFAULT_PROFILES[0]))
|
||||
for key in PROFILE_KEYS:
|
||||
if key in raw:
|
||||
base[key] = raw[key]
|
||||
for key in ("tool_probability", "split_probability", "timeout_probability", "failure_probability"):
|
||||
base[key] = clamp(float(base[key]), 0.0, 0.95)
|
||||
base["mean_subtasks"] = clamp(float(base["mean_subtasks"]), 1.0, 8.0)
|
||||
for key in ("think_time_ms_mean", "request_size_bytes_mean", "response_size_bytes_mean"):
|
||||
base[key] = max(float(base[key]), 1.0)
|
||||
for key in ("think_time_cv", "message_size_cv"):
|
||||
base[key] = clamp(float(base[key]), 0.05, 2.5)
|
||||
validated.append(base)
|
||||
found = {p["task_type"] for p in validated}
|
||||
for task_type in requested_types:
|
||||
if task_type not in found:
|
||||
validated.append(deepcopy(by_type.get(task_type, DEFAULT_PROFILES[0])))
|
||||
return [p for p in validated if p["task_type"] in requested_types]
|
||||
|
||||
|
||||
def generate_profiles(mode, task_types, llm_config, allow_fallback=True):
|
||||
if mode == "local":
|
||||
return _validate_profiles(DEFAULT_PROFILES, task_types), {"generator": "local_builtin"}
|
||||
|
||||
import os
|
||||
api_key = os.environ.get("OPENAI_API_KEY")
|
||||
base_url = os.environ.get("OPENAI_BASE_URL", "https://api.openai.com/v1").rstrip("/")
|
||||
model = os.environ.get("OPENAI_MODEL", "")
|
||||
if not api_key or not model:
|
||||
if allow_fallback:
|
||||
return _validate_profiles(DEFAULT_PROFILES, task_types), {
|
||||
"generator": "local_fallback", "reason": "OPENAI_API_KEY or OPENAI_MODEL missing"
|
||||
}
|
||||
raise RuntimeError("LLM mode requires OPENAI_API_KEY and OPENAI_MODEL")
|
||||
|
||||
prompt = f"""你是多智能体网络仿真实验的数据设计专家。请为以下任务类型生成行为画像：
|
||||
{json.dumps(task_types, ensure_ascii=False)}
|
||||
|
||||
仅输出 JSON 数组，每个对象必须包含这些字段：
|
||||
task_type, description, phase, tool_probability, split_probability, mean_subtasks,
|
||||
timeout_probability, failure_probability, think_time_ms_mean, think_time_cv,
|
||||
request_size_bytes_mean, response_size_bytes_mean, message_size_cv。
|
||||
|
||||
约束：概率在0到0.95之间；mean_subtasks在1到8之间；时间单位毫秒；消息大小单位字节；
|
||||
不同任务类型应体现从简单问答、工具密集到多Agent协作的明显差异。画像将用于科学仿真，数值应合理且可解释。"""
|
||||
payload = {
|
||||
"model": model,
|
||||
"messages": [
|
||||
{"role": "system", "content": "Return valid JSON only. Do not include markdown commentary."},
|
||||
{"role": "user", "content": prompt},
|
||||
],
|
||||
"temperature": float(llm_config.get("temperature", 0.5)),
|
||||
"max_tokens": int(llm_config.get("max_tokens", 3500)),
|
||||
}
|
||||
try:
|
||||
response = requests.post(
|
||||
base_url + "/chat/completions",
|
||||
headers={"Authorization": "Bearer " + api_key, "Content-Type": "application/json"},
|
||||
json=payload,
|
||||
timeout=float(llm_config.get("timeout_seconds", 90)),
|
||||
)
|
||||
response.raise_for_status()
|
||||
body = response.json()
|
||||
content = body["choices"][0]["message"]["content"]
|
||||
profiles = _validate_profiles(_extract_json(content), task_types)
|
||||
return profiles, {"generator": "llm", "model": model, "base_url": base_url}
|
||||
except Exception as exc:
|
||||
if not allow_fallback:
|
||||
raise
|
||||
return _validate_profiles(DEFAULT_PROFILES, task_types), {
|
||||
"generator": "local_fallback", "reason": str(exc), "requested_model": model
|
||||
}
|
||||
|
||||
|
||||
def _event(task_id, msg_id, parent_id, timestamp, task_type, phase, source, destination,
|
||||
state_before, state_after, duration, message_type, message_size, queue_length,
|
||||
success=True, retry_count=0, is_external=False):
|
||||
return {
|
||||
"timestamp": round(float(timestamp), 6),
|
||||
"task_id": task_id,
|
||||
"message_id": msg_id,
|
||||
"parent_message_id": parent_id or "",
|
||||
"task_type": task_type,
|
||||
"task_phase": phase,
|
||||
"source": source,
|
||||
"destination": destination,
|
||||
"state_before": state_before,
|
||||
"state_after": state_after,
|
||||
"state_duration_ms": round(float(duration), 3),
|
||||
"message_type": message_type,
|
||||
"message_size_bytes": int(max(0, round(message_size))),
|
||||
"queue_length": int(max(0, queue_length)),
|
||||
"success": bool(success),
|
||||
"retry_count": int(retry_count),
|
||||
"is_external": bool(is_external),
|
||||
}
|
||||
|
||||
|
||||
def generate_event_log(profiles, tasks_per_type, rng, network):
|
||||
events = []
|
||||
agent_count = int(network["agent_count"])
|
||||
tool_count = int(network["tool_count"])
|
||||
coordinator = network.get("coordinator", "agent_0")
|
||||
clock = 0.0
|
||||
for profile in profiles:
|
||||
for index in range(tasks_per_type):
|
||||
task_id = "%s_%05d" % (profile["task_type"], index)
|
||||
clock += float(rng.exponential(0.7))
|
||||
t = clock
|
||||
external_size = sample_lognormal(rng, profile["request_size_bytes_mean"] * 0.75,
|
||||
profile["message_size_cv"])
|
||||
root_id = uuid.uuid4().hex[:16]
|
||||
think = sample_lognormal(rng, profile["think_time_ms_mean"], profile["think_time_cv"])
|
||||
queue = int(rng.poisson(0.5 + 2.0 * profile["split_probability"]))
|
||||
events.append(_event(task_id, root_id, "", t, profile["task_type"], profile["phase"],
|
||||
"external", coordinator, "Idle", "Think", think,
|
||||
"external_task", external_size, queue, is_external=True))
|
||||
t += think / 1000.0
|
||||
parent = root_id
|
||||
split = rng.random() < profile["split_probability"]
|
||||
subtask_count = max(1, int(rng.poisson(max(profile["mean_subtasks"] - 1.0, 0.01)) + 1)) if split else 1
|
||||
subtask_count = min(subtask_count, 8)
|
||||
result_sizes = []
|
||||
all_success = True
|
||||
for sub_index in range(subtask_count):
|
||||
worker = "agent_%d" % (1 + ((index + sub_index) % max(1, agent_count - 1)))
|
||||
req_id = uuid.uuid4().hex[:16]
|
||||
req_size = sample_lognormal(rng, profile["request_size_bytes_mean"], profile["message_size_cv"])
|
||||
state = "Split" if split else "CallAgent"
|
||||
events.append(_event(task_id, req_id, parent, t, profile["task_type"], profile["phase"],
|
||||
coordinator, worker, "Think", state, 5.0, "agent_request",
|
||||
req_size, queue))
|
||||
worker_think = sample_lognormal(rng, profile["think_time_ms_mean"], profile["think_time_cv"])
|
||||
t += (8.0 + worker_think) / 1000.0
|
||||
tool_used = rng.random() < profile["tool_probability"]
|
||||
retries = 0
|
||||
success = True
|
||||
tool_response_size = 0.0
|
||||
if tool_used:
|
||||
tool = "tool_%d" % ((index + sub_index) % max(1, tool_count))
|
||||
tool_req_parent = req_id
|
||||
while True:
|
||||
tool_req_id = uuid.uuid4().hex[:16]
|
||||
tool_req_size = sample_lognormal(rng, profile["request_size_bytes_mean"] * 0.35,
|
||||
profile["message_size_cv"])
|
||||
events.append(_event(task_id, tool_req_id, tool_req_parent, t,
|
||||
profile["task_type"], profile["phase"], worker, tool,
|
||||
"Think" if retries == 0 else "Retry", "CallTool", 8.0,
|
||||
"tool_request", tool_req_size, queue, retry_count=retries))
|
||||
t += 0.008
|
||||
timed_out = rng.random() < profile["timeout_probability"]
|
||||
failed = rng.random() < profile["failure_probability"]
|
||||
if not timed_out and not failed:
|
||||
tool_response_size = sample_lognormal(
|
||||
rng, profile["response_size_bytes_mean"] * 0.72,
|
||||
profile["message_size_cv"])
|
||||
response_id = uuid.uuid4().hex[:16]
|
||||
tool_ms = sample_lognormal(rng, profile["think_time_ms_mean"] * 0.65,
|
||||
profile["think_time_cv"])
|
||||
t += tool_ms / 1000.0
|
||||
events.append(_event(task_id, response_id, tool_req_id, t,
|
||||
profile["task_type"], profile["phase"], tool, worker,
|
||||
"CallTool", "Think", tool_ms, "tool_response",
|
||||
tool_response_size, queue, retry_count=retries))
|
||||
break
|
||||
if retries >= 2:
|
||||
success = False
|
||||
fail_id = uuid.uuid4().hex[:16]
|
||||
events.append(_event(task_id, fail_id, tool_req_id, t + 2.2,
|
||||
profile["task_type"], profile["phase"], worker, coordinator,
|
||||
"Wait", "Failed", 2200.0, "error", 600, queue,
|
||||
success=False, retry_count=retries))
|
||||
t += 2.2
|
||||
break
|
||||
retries += 1
|
||||
t += 2.2 + 0.18 * retries
|
||||
result_id = uuid.uuid4().hex[:16]
|
||||
result_size = sample_lognormal(rng, profile["response_size_bytes_mean"],
|
||||
profile["message_size_cv"]) + tool_response_size * 0.15
|
||||
events.append(_event(task_id, result_id, req_id, t, profile["task_type"], profile["phase"],
|
||||
worker, coordinator, "Think", "Send" if success else "Failed", 5.0,
|
||||
"agent_response" if success else "error", result_size if success else 600,
|
||||
queue, success=success, retry_count=retries))
|
||||
result_sizes.append(result_size if success else 600)
|
||||
all_success = all_success and success
|
||||
t += 0.005
|
||||
final_id = uuid.uuid4().hex[:16]
|
||||
final_size = max(800.0, sum(result_sizes) * 0.38)
|
||||
final_think = sample_lognormal(rng, profile["think_time_ms_mean"] * 0.55,
|
||||
profile["think_time_cv"])
|
||||
t += final_think / 1000.0
|
||||
events.append(_event(task_id, final_id, parent, t, profile["task_type"], profile["phase"],
|
||||
coordinator, "external", "Think", "Send" if all_success else "Failed",
|
||||
final_think, "final_response" if all_success else "error", final_size,
|
||||
queue, success=all_success))
|
||||
return pd.DataFrame(events).sort_values(["timestamp", "task_id"]).reset_index(drop=True)
|
||||
|
||||
|
||||
def aggregate_task_truth(events):
|
||||
rows = []
|
||||
for task_id, group in events.groupby("task_id"):
|
||||
group = group.sort_values("timestamp")
|
||||
external = group[group["is_external"]]
|
||||
internal = group[~group["is_external"]]
|
||||
input_bytes = int(external["message_size_bytes"].sum())
|
||||
rows.append({
|
||||
"task_id": task_id,
|
||||
"task_type": group["task_type"].iloc[0],
|
||||
"task_phase": group["task_phase"].iloc[0],
|
||||
"latency_ms": max(0.0, (group["timestamp"].max() - group["timestamp"].min()) * 1000.0),
|
||||
"internal_bytes": int(internal["message_size_bytes"].sum()),
|
||||
"input_bytes": input_bytes,
|
||||
"amplification": float(internal["message_size_bytes"].sum()) / max(input_bytes, 1),
|
||||
"message_count": int(len(internal)),
|
||||
"tool_calls": int((group["message_type"] == "tool_request").sum()),
|
||||
"retries": int(group["retry_count"].max()),
|
||||
"success": bool(group["success"].all()),
|
||||
})
|
||||
return pd.DataFrame(rows)
|
||||
|
||||
@@ -0,0 +1,152 @@
|
||||
import json
|
||||
from pathlib import Path
|
||||
|
||||
import matplotlib
|
||||
matplotlib.use("Agg")
|
||||
import matplotlib.pyplot as plt
|
||||
import numpy as np
|
||||
import pandas as pd
|
||||
|
||||
from .simulator import simulate_queue_stress, simulate_task_batch
|
||||
|
||||
|
||||
def _metrics(actual, predicted):
|
||||
actual = np.asarray(actual, dtype=float)
|
||||
predicted = np.asarray(predicted, dtype=float)
|
||||
return {
|
||||
"mae": float(np.mean(np.abs(predicted - actual))),
|
||||
"rmse": float(np.sqrt(np.mean((predicted - actual) ** 2))),
|
||||
"mape_percent": float(np.mean(np.abs(predicted - actual) / np.maximum(np.abs(actual), 1e-9)) * 100.0),
|
||||
}
|
||||
|
||||
|
||||
def validation_experiment(truth, params, cfg, rng):
|
||||
scenario_truth = truth.groupby("task_type").agg(
|
||||
internal_bytes=("internal_bytes", "mean"),
|
||||
latency_ms=("latency_ms", "mean"),
|
||||
message_count=("message_count", "mean"),
|
||||
tool_calls=("tool_calls", "mean"),
|
||||
amplification=("amplification", "mean"),
|
||||
).reset_index()
|
||||
global_internal = float(scenario_truth["internal_bytes"].mean())
|
||||
global_latency = float(scenario_truth["latency_ms"].mean())
|
||||
rows = []
|
||||
n = int(cfg["experiments"]["validation_tasks_per_scenario"])
|
||||
for _, actual in scenario_truth.iterrows():
|
||||
task_type = actual["task_type"]
|
||||
for model in ("static_mean", "no_context", "full_model"):
|
||||
if model == "static_mean":
|
||||
prediction = {
|
||||
"internal_bytes": global_internal,
|
||||
"latency_ms": global_latency,
|
||||
"message_count": float(scenario_truth["message_count"].mean()),
|
||||
"tool_calls": float(scenario_truth["tool_calls"].mean()),
|
||||
"amplification": float(scenario_truth["amplification"].mean()),
|
||||
}
|
||||
else:
|
||||
samples = pd.DataFrame(simulate_task_batch(
|
||||
task_type, n, params, rng, max_retries=cfg["simulation"]["max_retries"],
|
||||
include_context=(model == "full_model"),
|
||||
))
|
||||
prediction = {key: float(samples[key].mean()) for key in
|
||||
("internal_bytes", "latency_ms", "message_count", "tool_calls", "amplification")}
|
||||
row = {"task_type": task_type, "model": model}
|
||||
for metric, pred in prediction.items():
|
||||
row["actual_" + metric] = float(actual[metric])
|
||||
row["predicted_" + metric] = pred
|
||||
rows.append(row)
|
||||
predictions = pd.DataFrame(rows)
|
||||
metric_rows = []
|
||||
for model, group in predictions.groupby("model"):
|
||||
for metric in ("internal_bytes", "latency_ms", "message_count", "tool_calls", "amplification"):
|
||||
values = _metrics(group["actual_" + metric], group["predicted_" + metric])
|
||||
metric_rows.append({"model": model, "metric": metric, **values})
|
||||
return predictions, pd.DataFrame(metric_rows)
|
||||
|
||||
|
||||
def stress_experiment(params, cfg, rng):
|
||||
task_type = "collaborative_analysis" if "collaborative_analysis" in params["task_types"] else list(params["task_types"])[-1]
|
||||
rows = []
|
||||
for rate in cfg["experiments"]["arrival_rates_per_second"]:
|
||||
rows.append(simulate_queue_stress(
|
||||
float(rate), cfg["experiments"]["stress_duration_seconds"],
|
||||
cfg["experiments"]["stress_warmup_seconds"], task_type, params, rng,
|
||||
max_concurrency=cfg["network"]["max_concurrency"],
|
||||
queue_capacity=cfg["network"]["queue_capacity"],
|
||||
max_retries=cfg["simulation"]["max_retries"],
|
||||
))
|
||||
return pd.DataFrame(rows)
|
||||
|
||||
|
||||
def retry_experiment(params, cfg, rng):
|
||||
task_type = "tool_research" if "tool_research" in params["task_types"] else list(params["task_types"])[0]
|
||||
rows = []
|
||||
for probability in cfg["experiments"]["timeout_probabilities"]:
|
||||
for retry_limit in cfg["experiments"]["retry_limits"]:
|
||||
samples = pd.DataFrame(simulate_task_batch(
|
||||
task_type, 240, params, rng, timeout_probability=float(probability),
|
||||
max_retries=int(retry_limit), include_context=True,
|
||||
))
|
||||
rows.append({
|
||||
"timeout_probability": probability,
|
||||
"max_retries": retry_limit,
|
||||
"success_rate": float(samples["success"].mean()),
|
||||
"mean_retries": float(samples["retries"].mean()),
|
||||
"mean_amplification": float(samples["amplification"].mean()),
|
||||
"mean_latency_ms": float(samples["latency_ms"].mean()),
|
||||
})
|
||||
return pd.DataFrame(rows)
|
||||
|
||||
|
||||
def make_figures(predictions, metrics, stress, retry, figure_dir):
|
||||
figure_dir = Path(figure_dir)
|
||||
plt.rcParams["font.sans-serif"] = ["Microsoft YaHei", "SimHei", "Arial Unicode MS", "DejaVu Sans"]
|
||||
plt.rcParams["axes.unicode_minus"] = False
|
||||
|
||||
full = predictions[predictions["model"] == "full_model"]
|
||||
fig, axes = plt.subplots(1, 2, figsize=(11, 4.5))
|
||||
for ax, metric, label in [(axes[0], "internal_bytes", "内部字节数"), (axes[1], "latency_ms", "任务延迟(ms)")]:
|
||||
x, y = full["actual_" + metric], full["predicted_" + metric]
|
||||
ax.scatter(x, y, s=65, color="#2E74B5")
|
||||
lo, hi = min(x.min(), y.min()), max(x.max(), y.max())
|
||||
ax.plot([lo, hi], [lo, hi], "--", color="#777777")
|
||||
for _, row in full.iterrows():
|
||||
ax.annotate(row["task_type"], (row["actual_" + metric], row["predicted_" + metric]), fontsize=8)
|
||||
ax.set_xlabel("模拟实测值"); ax.set_ylabel("模型预测值"); ax.set_title(label)
|
||||
ax.grid(alpha=0.25)
|
||||
fig.tight_layout(); fig.savefig(figure_dir / "prediction_vs_truth.png", dpi=180); plt.close(fig)
|
||||
|
||||
subset = metrics[metrics["metric"].isin(["internal_bytes", "latency_ms"])]
|
||||
pivot = subset.pivot(index="model", columns="metric", values="mape_percent")
|
||||
pivot = pivot.rename(
|
||||
index={"full_model": "完整模型", "no_context": "无上下文模型", "static_mean": "静态均值模型"},
|
||||
columns={"internal_bytes": "内部字节数", "latency_ms": "任务延迟"},
|
||||
)
|
||||
fig, ax = plt.subplots(figsize=(8, 4.6)); pivot.plot(kind="bar", ax=ax, color=["#2E74B5", "#70AD47"])
|
||||
ax.set_ylabel("MAPE (%)"); ax.set_xlabel("模型"); ax.set_title("完整模型与基线对比"); ax.grid(axis="y", alpha=0.25)
|
||||
ax.legend(title="指标")
|
||||
fig.tight_layout(); fig.savefig(figure_dir / "model_comparison.png", dpi=180); plt.close(fig)
|
||||
|
||||
fig, axes = plt.subplots(2, 2, figsize=(11, 7.5))
|
||||
axes[0, 0].plot(stress["arrival_rate"], stress["throughput_per_second"], marker="o")
|
||||
axes[0, 0].set_title("到达率—吞吐量")
|
||||
axes[0, 1].plot(stress["arrival_rate"], stress["p95_delay_ms"], marker="o", color="#C55A11")
|
||||
axes[0, 1].set_title("到达率—P95延迟")
|
||||
axes[1, 0].plot(stress["arrival_rate"], stress["queue_peak"], marker="o", color="#A5A5A5")
|
||||
axes[1, 0].set_title("到达率—峰值队列")
|
||||
axes[1, 1].plot(stress["arrival_rate"], stress["drop_rate"], marker="o", color="#C00000")
|
||||
axes[1, 1].set_title("到达率—丢弃率")
|
||||
for ax in axes.flat: ax.grid(alpha=0.25); ax.set_xlabel("任务/秒")
|
||||
fig.tight_layout(); fig.savefig(figure_dir / "stress_curves.png", dpi=180); plt.close(fig)
|
||||
|
||||
pivot = retry.pivot(index="timeout_probability", columns="max_retries", values="mean_amplification")
|
||||
fig, ax = plt.subplots(figsize=(8, 5)); image = ax.imshow(pivot.values, aspect="auto", cmap="YlOrRd")
|
||||
ax.set_xticks(range(len(pivot.columns)))
|
||||
ax.set_xticklabels([str(x) for x in pivot.columns])
|
||||
ax.set_yticks(range(len(pivot.index)))
|
||||
ax.set_yticklabels([str(x) for x in pivot.index])
|
||||
ax.set_xlabel("最大重试次数"); ax.set_ylabel("超时概率"); ax.set_title("重试导致的流量放大")
|
||||
for i in range(pivot.shape[0]):
|
||||
for j in range(pivot.shape[1]): ax.text(j, i, "%.2f" % pivot.iloc[i, j], ha="center", va="center", fontsize=8)
|
||||
fig.colorbar(image, ax=ax, label="平均流量放大系数")
|
||||
fig.tight_layout(); fig.savefig(figure_dir / "retry_heatmap.png", dpi=180); plt.close(fig)
|
||||
@@ -0,0 +1,67 @@
|
||||
from collections import defaultdict
|
||||
|
||||
import numpy as np
|
||||
|
||||
|
||||
def _stats(series, default=1.0):
|
||||
values = np.asarray(series, dtype=float)
|
||||
values = values[np.isfinite(values)]
|
||||
if len(values) == 0:
|
||||
return {"mean": default, "std": 0.0, "cv": 0.1, "p50": default, "p95": default, "count": 0}
|
||||
mean = float(np.mean(values))
|
||||
std = float(np.std(values))
|
||||
return {
|
||||
"mean": mean,
|
||||
"std": std,
|
||||
"cv": max(0.05, std / max(mean, 1e-9)),
|
||||
"p50": float(np.quantile(values, 0.50)),
|
||||
"p95": float(np.quantile(values, 0.95)),
|
||||
"count": int(len(values)),
|
||||
}
|
||||
|
||||
|
||||
def estimate_parameters(events):
|
||||
parameters = {"global": {}, "task_types": {}}
|
||||
transitions = events.groupby(["state_before", "state_after"]).size().to_dict()
|
||||
totals = events.groupby("state_before").size().to_dict()
|
||||
parameters["global"]["transition_probabilities"] = {
|
||||
"%s->%s" % key: float((count + 1.0) / (totals[key[0]] + 8.0))
|
||||
for key, count in transitions.items()
|
||||
}
|
||||
parameters["global"]["duration_ms"] = _stats(events["state_duration_ms"])
|
||||
parameters["global"]["message_size_bytes"] = _stats(events["message_size_bytes"])
|
||||
|
||||
for task_type, group in events.groupby("task_type"):
|
||||
tasks = group.groupby("task_id")
|
||||
task_count = max(1, group["task_id"].nunique())
|
||||
initial_tool_requests = group[(group["message_type"] == "tool_request") & (group["retry_count"] == 0)]
|
||||
agent_requests = group[group["message_type"] == "agent_request"]
|
||||
split_tasks = tasks["state_after"].apply(lambda s: (s == "Split").any())
|
||||
retry_tasks = tasks["retry_count"].max()
|
||||
tool_requests = group[group["message_type"] == "tool_request"]
|
||||
success_tasks = tasks["success"].all()
|
||||
external_sizes = group[group["is_external"]]["message_size_bytes"]
|
||||
request_sizes = group[group["message_type"].isin(["agent_request", "tool_request"])]["message_size_bytes"]
|
||||
response_sizes = group[group["message_type"].isin(["agent_response", "tool_response", "final_response"])]["message_size_bytes"]
|
||||
# 5-8ms values represent message-send bookkeeping, not reasoning/service time.
|
||||
think_durations = group[
|
||||
(group["state_duration_ms"] > 20.0)
|
||||
& (group["message_type"].isin(["external_task", "tool_response", "final_response"]))
|
||||
]["state_duration_ms"]
|
||||
subtask_counts = tasks["message_type"].apply(lambda s: int((s == "agent_request").sum()))
|
||||
parameters["task_types"][task_type] = {
|
||||
"phase": str(group["task_phase"].mode().iloc[0]),
|
||||
"task_count": task_count,
|
||||
"tool_probability": float(len(initial_tool_requests) / max(len(agent_requests), 1)),
|
||||
"split_probability": float(split_tasks.mean()),
|
||||
"mean_subtasks": float(subtask_counts.mean()),
|
||||
"retry_probability": float((tool_requests["retry_count"] > 0).sum() / max(len(tool_requests), 1)),
|
||||
"mean_retries_if_any": float(retry_tasks[retry_tasks > 0].mean()) if (retry_tasks > 0).any() else 0.0,
|
||||
"failure_probability": float((~success_tasks).mean()),
|
||||
"think_time_ms": _stats(think_durations, 500.0),
|
||||
"external_size_bytes": _stats(external_sizes, 1500.0),
|
||||
"request_size_bytes": _stats(request_sizes, 2000.0),
|
||||
"response_size_bytes": _stats(response_sizes, 4000.0),
|
||||
"message_count_per_task": _stats(tasks.size(), 3.0),
|
||||
}
|
||||
return parameters
|
||||
@@ -0,0 +1,176 @@
|
||||
import heapq
|
||||
import itertools
|
||||
import math
|
||||
from collections import defaultdict, deque
|
||||
|
||||
import numpy as np
|
||||
|
||||
from .common import sample_lognormal
|
||||
|
||||
|
||||
def simulate_task_batch(task_type, task_count, params, rng, timeout_probability=None,
|
||||
max_retries=2, include_context=True):
|
||||
task_params = params["task_types"][task_type] if include_context else _globalized(params)
|
||||
rows = []
|
||||
for _ in range(task_count):
|
||||
split = rng.random() < task_params["split_probability"]
|
||||
subtasks = max(1, int(rng.poisson(max(task_params["mean_subtasks"] - 1.0, 0.01)) + 1)) if split else 1
|
||||
subtasks = min(subtasks, 8)
|
||||
input_size = sample_lognormal(rng, task_params["external_size_bytes"]["mean"],
|
||||
task_params["external_size_bytes"]["cv"])
|
||||
total_bytes = 0.0
|
||||
messages = 0
|
||||
tool_calls = 0
|
||||
retries_total = 0
|
||||
success = True
|
||||
durations = []
|
||||
coordinator_think = sample_lognormal(rng, task_params["think_time_ms"]["mean"],
|
||||
task_params["think_time_ms"]["cv"])
|
||||
durations.append(coordinator_think)
|
||||
for _sub in range(subtasks):
|
||||
tool = rng.random() < task_params["tool_probability"]
|
||||
req = sample_lognormal(rng, task_params["request_size_bytes"]["mean"],
|
||||
task_params["request_size_bytes"]["cv"])
|
||||
total_bytes += req
|
||||
messages += 1
|
||||
worker_time = sample_lognormal(rng, task_params["think_time_ms"]["mean"],
|
||||
task_params["think_time_ms"]["cv"])
|
||||
durations.append(worker_time)
|
||||
if tool:
|
||||
p_timeout = task_params["retry_probability"] if timeout_probability is None else timeout_probability
|
||||
attempts = 0
|
||||
tool_success = False
|
||||
while attempts <= max_retries:
|
||||
tool_calls += 1
|
||||
tool_req = sample_lognormal(rng, task_params["request_size_bytes"]["mean"] * 0.35,
|
||||
task_params["request_size_bytes"]["cv"])
|
||||
total_bytes += tool_req
|
||||
messages += 1
|
||||
timed_out = rng.random() < p_timeout
|
||||
if not timed_out:
|
||||
tool_resp = sample_lognormal(rng, task_params["response_size_bytes"]["mean"] * 0.72,
|
||||
task_params["response_size_bytes"]["cv"])
|
||||
total_bytes += tool_resp
|
||||
messages += 1
|
||||
durations.append(sample_lognormal(rng, task_params["think_time_ms"]["mean"] * 0.65,
|
||||
task_params["think_time_ms"]["cv"]))
|
||||
tool_success = True
|
||||
break
|
||||
if attempts < max_retries:
|
||||
retries_total += 1
|
||||
durations.append(2200.0 + 180.0 * (attempts + 1))
|
||||
attempts += 1
|
||||
success = success and tool_success
|
||||
response = sample_lognormal(rng, task_params["response_size_bytes"]["mean"],
|
||||
task_params["response_size_bytes"]["cv"])
|
||||
total_bytes += response if success else 600.0
|
||||
messages += 1
|
||||
final_size = max(800.0, subtasks * task_params["response_size_bytes"]["mean"] * 0.38)
|
||||
total_bytes += final_size
|
||||
messages += 1
|
||||
latency = sum(durations) + 8.0 * messages
|
||||
rows.append({
|
||||
"task_type": task_type,
|
||||
"internal_bytes": total_bytes,
|
||||
"input_bytes": input_size,
|
||||
"amplification": total_bytes / max(input_size, 1.0),
|
||||
"latency_ms": latency,
|
||||
"message_count": messages,
|
||||
"tool_calls": tool_calls,
|
||||
"retries": retries_total,
|
||||
"success": success,
|
||||
})
|
||||
return rows
|
||||
|
||||
|
||||
def _globalized(params):
|
||||
entries = list(params["task_types"].values())
|
||||
def mean(name):
|
||||
return float(np.mean([e[name] for e in entries]))
|
||||
def stat(name):
|
||||
return {
|
||||
"mean": float(np.mean([e[name]["mean"] for e in entries])),
|
||||
"cv": float(np.mean([e[name]["cv"] for e in entries])),
|
||||
}
|
||||
return {
|
||||
"tool_probability": mean("tool_probability"),
|
||||
"split_probability": mean("split_probability"),
|
||||
"mean_subtasks": mean("mean_subtasks"),
|
||||
"retry_probability": mean("retry_probability"),
|
||||
"failure_probability": mean("failure_probability"),
|
||||
"think_time_ms": stat("think_time_ms"),
|
||||
"external_size_bytes": stat("external_size_bytes"),
|
||||
"request_size_bytes": stat("request_size_bytes"),
|
||||
"response_size_bytes": stat("response_size_bytes"),
|
||||
}
|
||||
|
||||
|
||||
def simulate_queue_stress(arrival_rate, duration_seconds, warmup_seconds, task_type, params,
|
||||
rng, max_concurrency=4, queue_capacity=500, timeout_probability=None,
|
||||
max_retries=2):
|
||||
tasks = simulate_task_batch(
|
||||
task_type, max(200, int(arrival_rate * duration_seconds * 1.5)), params, rng,
|
||||
timeout_probability=timeout_probability, max_retries=max_retries,
|
||||
)
|
||||
event_queue = []
|
||||
counter = itertools.count()
|
||||
time = 0.0
|
||||
task_index = 0
|
||||
while time < duration_seconds:
|
||||
time += float(rng.exponential(1.0 / max(arrival_rate, 1e-9)))
|
||||
if time <= duration_seconds:
|
||||
heapq.heappush(event_queue, (time, next(counter), "arrival", task_index))
|
||||
task_index += 1
|
||||
|
||||
waiting = deque()
|
||||
busy = 0
|
||||
completed = []
|
||||
dropped = 0
|
||||
queue_peak = 0
|
||||
arrival_times = {}
|
||||
while event_queue:
|
||||
now, _, event_type, idx = heapq.heappop(event_queue)
|
||||
if event_type == "arrival":
|
||||
arrival_times[idx] = now
|
||||
if busy < max_concurrency:
|
||||
busy += 1
|
||||
task = tasks[idx % len(tasks)]
|
||||
service = task["latency_ms"] / 1000.0
|
||||
heapq.heappush(event_queue, (now + service, next(counter), "complete", idx))
|
||||
elif len(waiting) < queue_capacity:
|
||||
waiting.append(idx)
|
||||
queue_peak = max(queue_peak, len(waiting))
|
||||
else:
|
||||
dropped += 1
|
||||
else:
|
||||
task = tasks[idx % len(tasks)]
|
||||
if arrival_times[idx] >= warmup_seconds:
|
||||
record = dict(task)
|
||||
record["end_to_end_ms"] = (now - arrival_times[idx]) * 1000.0
|
||||
completed.append(record)
|
||||
busy -= 1
|
||||
if waiting:
|
||||
nxt = waiting.popleft()
|
||||
busy += 1
|
||||
task2 = tasks[nxt % len(tasks)]
|
||||
heapq.heappush(event_queue, (now + task2["latency_ms"] / 1000.0,
|
||||
next(counter), "complete", nxt))
|
||||
offered = max(1, task_index)
|
||||
if completed:
|
||||
delays = np.array([x["end_to_end_ms"] for x in completed])
|
||||
amps = np.array([x["amplification"] for x in completed])
|
||||
success = np.array([x["success"] for x in completed], dtype=float)
|
||||
else:
|
||||
delays, amps, success = np.array([0.0]), np.array([0.0]), np.array([0.0])
|
||||
return {
|
||||
"arrival_rate": arrival_rate,
|
||||
"offered_tasks": offered,
|
||||
"completed_tasks": len(completed),
|
||||
"throughput_per_second": len(completed) / max(duration_seconds - warmup_seconds, 1),
|
||||
"mean_delay_ms": float(delays.mean()),
|
||||
"p95_delay_ms": float(np.quantile(delays, 0.95)),
|
||||
"queue_peak": queue_peak,
|
||||
"drop_rate": dropped / offered,
|
||||
"success_rate": float(success.mean()),
|
||||
"mean_amplification": float(amps.mean()),
|
||||
}
|
||||
@@ -0,0 +1,29 @@
|
||||
param([Parameter(Mandatory=$true)][string]$OutputPath)
|
||||
$ErrorActionPreference='Stop'
|
||||
$word=New-Object -ComObject Word.Application
|
||||
$word.Visible=$false
|
||||
$word.DisplayAlerts=0
|
||||
try {
|
||||
$doc=$word.Documents.Add()
|
||||
try {
|
||||
$doc.PageSetup.PaperSize=2
|
||||
$doc.PageSetup.TopMargin=$word.InchesToPoints(0.85)
|
||||
$doc.PageSetup.BottomMargin=$word.InchesToPoints(0.8)
|
||||
$doc.PageSetup.LeftMargin=$word.InchesToPoints(0.9)
|
||||
$doc.PageSetup.RightMargin=$word.InchesToPoints(0.9)
|
||||
$normal=$doc.Styles.Item(-1)
|
||||
$normal.Font.Name='Calibri'; $normal.Font.NameFarEast='Microsoft YaHei'; $normal.Font.Size=10.5
|
||||
$normal.ParagraphFormat.SpaceAfter=6; $normal.ParagraphFormat.LineSpacingRule=5; $normal.ParagraphFormat.LineSpacing=15
|
||||
$title=$doc.Styles.Item(-63)
|
||||
$title.Font.Name='Calibri'; $title.Font.NameFarEast='Microsoft YaHei'; $title.Font.Size=25; $title.Font.Bold=$true; $title.Font.Color=9655585
|
||||
$title.ParagraphFormat.Alignment=1; $title.ParagraphFormat.SpaceBefore=100; $title.ParagraphFormat.SpaceAfter=12
|
||||
$subtitle=$doc.Styles.Item(-75)
|
||||
$subtitle.Font.Name='Calibri'; $subtitle.Font.NameFarEast='Microsoft YaHei'; $subtitle.Font.Size=14; $subtitle.Font.Color=8421504
|
||||
$subtitle.ParagraphFormat.Alignment=1; $subtitle.ParagraphFormat.SpaceAfter=24
|
||||
foreach($pair in @(@(-2,16,16,8,11621185),@(-3,13,12,6,11621185),@(-4,11.5,9,4,9655585))){
|
||||
$s=$doc.Styles.Item($pair[0]); $s.Font.Name='Calibri'; $s.Font.NameFarEast='Microsoft YaHei'; $s.Font.Size=$pair[1]; $s.Font.Bold=$true; $s.Font.Color=$pair[4]
|
||||
$s.ParagraphFormat.SpaceBefore=$pair[2]; $s.ParagraphFormat.SpaceAfter=$pair[3]; $s.ParagraphFormat.KeepWithNext=$true
|
||||
}
|
||||
$doc.SaveAs2($OutputPath,16)
|
||||
} finally { $doc.Close($true); [Runtime.InteropServices.Marshal]::ReleaseComObject($doc)|Out-Null }
|
||||
} finally { $word.Quit(); [Runtime.InteropServices.Marshal]::ReleaseComObject($word)|Out-Null }
|
||||
@@ -0,0 +1,357 @@
|
||||
---
|
||||
title: "大规模多智能体网络流量建模与预测"
|
||||
subtitle: "整体设计思路（参赛材料初稿）"
|
||||
author: "参赛团队：待填写"
|
||||
date: "2026年8月"
|
||||
toc: true
|
||||
toc-title: "目录"
|
||||
number-sections: true
|
||||
---
|
||||
|
||||
# 本次修订说明
|
||||
|
||||
**修订日期：2026年8月13日**
|
||||
|
||||
本版本在原有整体设计框架上增加了“模拟实验设计流程”，主要改动如下：
|
||||
|
||||
- 在“数据与参数设计”章节新增 **5.3 模拟实验设计流程**；
|
||||
- 增加“场景定义—大模型生成行为画像—参数校验—结构化日志生成—训练集估参—验证集调参—测试集评估—实验输出”的完整闭环；
|
||||
- 说明大模型只生成少量任务行为画像，本地程序负责扩展大量事件日志，以保证消息关系、时间顺序和统计口径一致；
|
||||
- 增加模拟实验各环节的工作内容和质量控制表；
|
||||
- 明确实验支持无 API Key 的本地画像模式和兼容 OpenAI 接口的 LLM 模式；
|
||||
- 将答辩 PPT 建议由 14 页调整为 15 页，新增“模拟实验设计流程”展示页；
|
||||
- 强调模拟数据用于快速验证模型机制，不等同于真实生产日志，后续需要使用真实数据校准。
|
||||
|
||||
对应实验代码位于 `agent_traffic_experiments/`，可生成事件日志、估计参数并运行预测验证、基线对比、压力和重试实验。
|
||||
|
||||
# 项目摘要
|
||||
|
||||
随着大语言模型从单体问答逐步发展为多智能体协作系统，任务拆分、Agent 间协商、工具调用、数据查询、结果回传和超时重试会产生大量内部消息。系统规模扩大后，通信流量不再只由用户请求量决定，还受到节点能力、任务阶段、网络拓扑、队列负载和故障重试的共同影响。传统的静态流量估算或单一排队模型难以还原这种“业务行为驱动网络流量”的动态过程。
|
||||
|
||||
本项目提出一套面向大规模 Agent 网络的流量建模与预测方案。方案以动态通信图描述节点连接，以外层状态机描述消息跨节点传播，以内层状态机描述节点接收、排队、思考、调用、等待、重试和发送等行为，并采用离散事件仿真计算节点流量、链路负载、端到端时延、队列长度和故障放大效应。模型参数可从小规模 Agent 运行日志和压力测试中估计，再通过分层参数和能力特征推广到更大规模网络。
|
||||
|
||||
> 核心设计：动态通信图 + 双层随机状态机 + 消息队列 + 离散事件仿真 + 分层参数学习 + 流量与拥塞评估。
|
||||
|
||||
# 一、研究背景与问题提出
|
||||
|
||||
## 1.1 背景
|
||||
|
||||
典型的多智能体系统通常包含协调 Agent、执行 Agent、检索服务、工具服务、数据库以及模型推理服务。一次外部任务可能经历如下过程：
|
||||
|
||||
1. 协调节点解析任务并拆分子任务；
|
||||
2. 多个执行节点并行处理；
|
||||
3. 执行节点调用工具或查询数据；
|
||||
4. 工具结果返回后继续推理；
|
||||
5. 失败请求触发超时、重试或改道；
|
||||
6. 协调节点汇总结果并返回用户。
|
||||
|
||||
因此，一条外部请求可能放大为数十条内部消息。随着 Agent 数量和并发任务增加，系统会出现热点节点、队列堆积、链路拥塞、超时重试放大等现象。若无法提前预测这些行为，就难以完成容量规划、资源调度和可靠性设计。
|
||||
|
||||
## 1.2 现有方法的不足
|
||||
|
||||
- **静态倍数估算**只能给出平均流量，不能描述任务阶段和故障状态下的变化。
|
||||
- **单纯拓扑模型**只能说明节点是否可达，不能说明节点为何产生新消息。
|
||||
- **单一排队模型**能够分析等待时间，但难以表达拆分、工具调用和多轮协作。
|
||||
- **完全数据驱动模型**需要大量大规模真实日志，冷启动成本高且解释性不足。
|
||||
|
||||
## 1.3 核心问题
|
||||
|
||||
本项目试图解决三个问题：
|
||||
|
||||
1. 如何用统一模型描述不同 Agent、工具和服务的通信行为？
|
||||
2. 如何从小规模日志估计参数，并推演大规模网络的流量和延迟？
|
||||
3. 如何刻画“拥塞—超时—重试—流量增加”的动态反馈过程？
|
||||
|
||||
# 二、项目目标与应用价值
|
||||
|
||||
## 2.1 建模目标
|
||||
|
||||
给定网络拓扑、节点能力、外部任务负载及行为参数，模型输出：
|
||||
|
||||
- 每个节点的入站和出站消息率、字节流量；
|
||||
- 每条链路的消息数、字节数及带宽利用率；
|
||||
- 任务平均时延以及 P95、P99 尾延迟；
|
||||
- 节点队列长度、资源利用率和吞吐量；
|
||||
- 消息平均跳数、任务内部消息数和流量放大系数；
|
||||
- 超时、失败和重试条件下的额外流量；
|
||||
- 热点节点、瓶颈链路和系统容量拐点。
|
||||
|
||||
## 2.2 应用价值
|
||||
|
||||
| 应用场景 | 模型提供的能力 | 可支持的决策 |
|
||||
|---|---|---|
|
||||
| 上线前容量规划 | 预测不同任务量下的节点与链路负载 | 配置并发数、实例数和带宽 |
|
||||
| Agent 编排优化 | 比较不同拓扑和路由策略 | 减少跳数、热点与无效协作 |
|
||||
| 故障与可靠性设计 | 模拟节点故障、超时和重试 | 选择重试次数、退避策略和备用节点 |
|
||||
| 在线运维 | 根据日志校准模型并识别偏差 | 发现异常流量和潜在拥塞 |
|
||||
| 成本评估 | 估计内部消息量、字节量和工具调用次数 | 对比不同架构的通信与计算成本 |
|
||||
|
||||
# 三、总体设计框架
|
||||
|
||||
## 3.1 总体技术路线
|
||||
|
||||
项目分为数据层、参数层、模型层、仿真层和评估层。
|
||||
|
||||
```text
|
||||
Agent运行日志、拓扑配置、压力测试数据
|
||||
↓
|
||||
数据清洗、任务链还原、特征提取
|
||||
↓
|
||||
状态转移概率 / 持续时间 / 消息大小 / 失败与重试参数
|
||||
↓
|
||||
动态通信图 + 外层传播状态机 + 内层节点状态机 + 队列模型
|
||||
↓
|
||||
离散事件仿真
|
||||
↓
|
||||
节点流量 / 链路流量 / 延迟 / 吞吐量 / 拥塞 / 可靠性
|
||||
↓
|
||||
实测对比、基线对比、消融和压力实验
|
||||
```
|
||||
|
||||
## 3.2 五层架构
|
||||
|
||||
| 层次 | 主要内容 | 关键产物 |
|
||||
|---|---|---|
|
||||
| 数据层 | 采集任务、消息、状态、队列和链路日志 | 标准化事件日志 |
|
||||
| 参数层 | 估计概率、分布、容量和路由参数 | 参数配置与置信度 |
|
||||
| 模型层 | 图模型、双层状态机、队列和流量公式 | 数学模型 |
|
||||
| 仿真层 | 事件队列、状态更新、消息生成和统计 | 可运行仿真器 |
|
||||
| 评估层 | 正确性、精度、扩展性和鲁棒性验证 | 实验报告与图表 |
|
||||
|
||||
# 四、核心模型设计
|
||||
|
||||
## 4.1 动态通信图
|
||||
|
||||
系统表示为随时间变化的有向图：
|
||||
|
||||
$$
|
||||
G(t)=(V(t),E(t))
|
||||
$$
|
||||
|
||||
其中节点可以是 Agent、模型服务、工具或数据库，边表示允许的通信关系。节点不被永久划分为固定角色，而是通过能力向量描述：
|
||||
|
||||
```text
|
||||
can_reason, can_split_task, can_call_tool,
|
||||
can_query_database, can_forward, max_concurrency
|
||||
```
|
||||
|
||||
同一个节点可以在不同任务阶段承担协调、执行、查询或转发功能，从而提高模型对异构系统和新节点的适应能力。
|
||||
|
||||
## 4.2 外层状态机：消息如何跨节点传播
|
||||
|
||||
外层状态机描述消息当前所在节点、路径位置、交互上下文以及下一目标节点。它回答“消息去哪里”的问题。
|
||||
|
||||
```text
|
||||
外部任务 → 协调节点 → 执行节点 → 工具节点
|
||||
↓ ↑
|
||||
等待结果 ← 返回结果
|
||||
↓
|
||||
协调节点 → 外部系统
|
||||
```
|
||||
|
||||
目标节点选择同时考虑可达性、节点能力、网络距离、队列负载和链路利用率。
|
||||
|
||||
## 4.3 内层状态机：节点收到消息后做什么
|
||||
|
||||
模型严格区分节点资源状态和消息处理状态：节点资源状态 $q_v\in\{Idle,Busy,Saturated,Failed\}$ 描述节点整体的资源占用情况；消息处理状态 $q_m$ 描述一条消息或任务处理上下文当前所处的业务阶段。下面的状态机属于 $q_m$，同一节点可以同时维护多个 $q_m$，但活跃上下文数量不得超过 `max_concurrency`。
|
||||
|
||||
所有节点共享一套通用状态集合：
|
||||
|
||||
```text
|
||||
Idle → Receive → Queue → Think
|
||||
├→ Send
|
||||
├→ Split → Wait
|
||||
├→ CallAgent → Wait
|
||||
├→ CallTool → Wait
|
||||
├→ Query → Wait
|
||||
└→ Forward → Wait
|
||||
Wait → Think / Retry → Failed
|
||||
Send / Failed → Idle
|
||||
```
|
||||
|
||||
能力和拓扑先决定某个动作是否可行，条件概率模型再在可行动作中选择下一状态。例如，没有工具调用能力或邻域中没有可用工具时，`Think → CallTool` 的概率直接为零。
|
||||
|
||||
## 4.4 分层参数与小样本泛化
|
||||
|
||||
状态转移概率不是所有节点共用的固定常数，而是由任务、阶段、能力、拓扑和负载共同决定：
|
||||
|
||||
$$
|
||||
P(q'\mid q,c,x_v,z_v,m,\ell_v)
|
||||
$$
|
||||
|
||||
采用“全局基础参数—任务修正—阶段修正—能力修正—拓扑与负载修正”的分层结构。新任务或新节点数据不足时，先回退到相似类别或全局参数，并记录参数来源和可信度；获得新日志后再增量校准。
|
||||
|
||||
## 4.5 消息队列与拥塞反馈
|
||||
|
||||
节点队列随到达和服务动态变化：
|
||||
|
||||
$$
|
||||
Q_v(t+\Delta t)=\max\{0,Q_v(t)+A_v(t)-D_v(t)\}
|
||||
$$
|
||||
|
||||
其中 $Q_v(t)$ 只统计已经到达节点、但尚未获得活跃处理资源的消息；正在 `Think`、`CallTool` 或 `Wait` 中的上下文不计入队列。$D_v$ 表示从等待队列取出并开始处理的消息数，而不是处理完成数。队列采用有界、按 `priority` 优先且同优先级按到达顺序处理的规则。默认情况下 `Wait` 状态仍占用并发槽；若实际系统等待期间释放资源，应显式配置 `wait_holds_slot=false`。
|
||||
|
||||
当到达率接近或超过处理能力时，等待时间增加并可能触发超时。超时产生重试消息，进一步增加队列和链路负载，从而形成反馈闭环：
|
||||
|
||||
```text
|
||||
负载上升 → 排队增长 → 延迟上升 → 超时增多
|
||||
↑ ↓
|
||||
└──────── 重试消息增加 ←───────────┘
|
||||
```
|
||||
|
||||
## 4.6 离散事件仿真
|
||||
|
||||
采用事件驱动方式，只在事件发生时更新状态。主要事件包括外部任务到达、消息到达、处理开始、状态完成、发送完成、工具返回、请求超时、重试和故障。
|
||||
|
||||
每次处理事件时：
|
||||
|
||||
1. 读取节点、消息、任务阶段和当前负载；
|
||||
2. 过滤不可行的状态转移；
|
||||
3. 计算并抽样下一状态及持续时间；
|
||||
4. 生成输出消息并选择目标节点；
|
||||
5. 更新节点队列、链路状态和流量统计；
|
||||
6. 把后续事件加入全局优先队列。
|
||||
|
||||
# 五、数据与参数设计
|
||||
|
||||
## 5.1 最小日志字段
|
||||
|
||||
| 字段组 | 字段 | 主要用途 |
|
||||
|---|---|---|
|
||||
| 标识 | task_id、message_id、parent_message_id、correlation_id、attempt_id | 还原任务调用链、匹配请求响应并区分重试尝试 |
|
||||
| 时间 | timestamp、state_start、state_end | 估计状态时间和端到端延迟 |
|
||||
| 路由 | source、destination、next_hop、path、hop | 区分逻辑终点与实际下一跳，统计有向链路流量 |
|
||||
| 业务 | task_type、task_phase、message_type | 分层估计参数 |
|
||||
| 状态 | state_before、state_after | 估计状态转移概率 |
|
||||
| 负载 | queue_length、concurrency、link_utilization | 估计排队和拥塞效应 |
|
||||
| 结果 | message_size、success、retry_count | 估计字节流量与可靠性 |
|
||||
|
||||
## 5.2 参数来源
|
||||
|
||||
- 系统配置：节点能力、并发上限、队列容量和链路带宽；
|
||||
- 小规模日志：状态转移、消息大小、目标选择和处理时间；
|
||||
- 压力测试：高负载下服务速度、超时率和失败率；
|
||||
- 场景假设：尚无数据参数的初始范围；
|
||||
- 仿真校准：根据验证集误差选择分布和调整参数；测试集仅用于最终评估。
|
||||
|
||||
## 5.3 模拟实验设计流程
|
||||
|
||||
在真实大规模 Agent 日志暂不充足的阶段，项目采用“大模型生成行为画像、本地程序扩展结构化日志、状态机模型完成仿真验证”的快速实验路线。大模型不直接逐行编造数万条日志，而是生成少量可解释的任务行为参数，再由受约束的数据生成器保证消息关系、时间顺序和流量统计一致。
|
||||
|
||||
```text
|
||||
设定任务类型与网络场景
|
||||
↓
|
||||
大模型生成任务行为画像
|
||||
工具调用率 / 拆分率 / 子任务数 / 处理时间 / 消息大小 / 超时率
|
||||
↓
|
||||
画像校验与参数约束
|
||||
概率范围检查 / 必填字段检查 / 缺失参数回退
|
||||
↓
|
||||
本地随机引擎生成结构化事件日志
|
||||
task_id / message_id / 状态转移 / 节点路径 / 字节数 / 时间戳
|
||||
↓
|
||||
训练集估计模型参数，验证集选择分布和调整参数
|
||||
↓
|
||||
测试集仅保留为模拟实测值并用于最终评估
|
||||
↓
|
||||
运行双层状态机与离散事件仿真
|
||||
↓
|
||||
基线对比 / 压力实验 / 重试放大实验
|
||||
↓
|
||||
输出 CSV、参数 JSON 和报告图表
|
||||
```
|
||||
|
||||
| 环节 | 主要工作 | 质量控制 |
|
||||
|---|---|---|
|
||||
| 场景定义 | 设置简单问答、工具研究、多 Agent 协作等任务 | 保证任务复杂度具有明显梯度 |
|
||||
| LLM 画像生成 | 生成状态概率、处理时间、消息大小和故障参数 | 限定字段、单位和数值范围 |
|
||||
| 日志扩展 | 将画像扩展为可统计的任务与消息事件 | 保证 ID 唯一、父子消息可追踪、时间单调 |
|
||||
| 参数估计 | 从训练日志估计分层模型参数 | 测试数据不参与估参 |
|
||||
| 模型实验 | 执行预测、基线、压力和重试实验 | 固定随机种子，多次重复 |
|
||||
| 结果解释 | 形成误差表、容量曲线和重试热力图 | 明确标注为模拟数据，不替代真实验证 |
|
||||
|
||||
当前实验工程支持两种模式：没有 API Key 时使用内置行为画像立即跑通；配置兼容 OpenAI 接口后，由大模型生成画像。后续获得真实日志时，可以保持实验流程不变，只替换或校准画像和参数。
|
||||
|
||||
# 六、方案创新点
|
||||
|
||||
## 6.1 双层状态机实现业务行为与网络传播解耦
|
||||
|
||||
外层描述消息路径，内层描述节点行为。两层分别清晰、组合后又能完整计算流量，避免把所有节点和动作塞入一个不可维护的巨型状态机。
|
||||
|
||||
## 6.2 能力驱动的统一节点表示
|
||||
|
||||
使用能力向量和上下文决定行为，不依赖固定节点类型，使模型能够支持新节点、角色动态变化和异构 Agent 网络。
|
||||
|
||||
## 6.3 小规模日志到大规模网络的分层推广
|
||||
|
||||
通过共享基础参数、条件修正和回退机制减少对海量真实数据的依赖，同时保留参数解释性和可信度标记。
|
||||
|
||||
## 6.4 显式描述重试流量放大闭环
|
||||
|
||||
模型不仅计算正常通信，还刻画排队、超时、失败、重试对流量的反向影响，可用于发现系统容量拐点和故障雪崩风险。
|
||||
|
||||
# 七、验证思路
|
||||
|
||||
验证工作分为五个层次：
|
||||
|
||||
1. **程序正确性**：三节点手工算例与仿真逐事件对账；
|
||||
2. **预测准确性**：训练日志估参、测试日志比较节点流量和延迟；
|
||||
3. **模型必要性**：与静态倍数、纯拓扑和简单排队基线比较；
|
||||
4. **模块贡献**：移除队列、阶段、拓扑或重试模块进行消融；
|
||||
5. **大规模能力**：在 10 至 100000 个仿真节点上测试时间和内存开销。
|
||||
|
||||
主要指标包括 MAE、RMSE、MAPE、P95/P99 延迟误差、热点识别准确率、事件处理吞吐量和内存占用。
|
||||
|
||||
# 八、预期成果
|
||||
|
||||
## 8.1 软件成果
|
||||
|
||||
- 网络场景与参数配置模块；
|
||||
- 日志解析和参数估计模块；
|
||||
- 双层状态机离散事件仿真器；
|
||||
- 节点、链路和任务级统计模块；
|
||||
- 实验脚本和可视化看板。
|
||||
|
||||
## 8.2 文档成果
|
||||
|
||||
- 整体设计思路；
|
||||
- 数学建模方案；
|
||||
- 验证与评估报告；
|
||||
- 用户说明、参数字典和复现实验说明。
|
||||
|
||||
## 8.3 预期图表
|
||||
|
||||
- 总体技术路线图和双层状态机图；
|
||||
- 网络节点负载热力图与链路流量图；
|
||||
- 预测值与实测值对比图；
|
||||
- 到达率—吞吐量—延迟曲线；
|
||||
- 超时概率—重试流量放大曲线；
|
||||
- 节点规模—仿真运行时间/内存曲线。
|
||||
|
||||
# 九、实施计划与风险控制
|
||||
|
||||
| 阶段 | 工作内容 | 阶段产物 |
|
||||
|---|---|---|
|
||||
| 第一阶段 | 固化问题、状态和参数定义 | 建模方案 V1 |
|
||||
| 第二阶段 | 实现 3—10 节点最小仿真 | 可运行原型与手工对账 |
|
||||
| 第三阶段 | 构造日志、完成参数估计和基线 | 数据集与实验脚本 |
|
||||
| 第四阶段 | 压力、消融、故障和规模实验 | 实验结果与图表 |
|
||||
| 第五阶段 | 完成报告、PPT和答辩材料 | 正式参赛材料 |
|
||||
|
||||
主要风险及应对措施：
|
||||
|
||||
- **真实日志不足**：先使用可解释的合成场景，明确标注参数来源，再逐步替换为实测参数；
|
||||
- **大规模运行开销过高**：使用事件驱动、稀疏图、节点聚合和分区仿真；
|
||||
- **状态空间过大**：保持通用状态机，具体差异放入能力和参数，而非无限增加状态；
|
||||
- **结果可信度不足**：保留参数来源、置信区间、基线对比和误差分析；
|
||||
- **比赛叙事过于技术化**：用“容量规划、热点定位、重试雪崩预警”贯穿展示。
|
||||
|
||||
# 十、答辩PPT映射建议
|
||||
|
||||
本设计书可以压缩为 15 页答辩 PPT：
|
||||
|
||||
1. 项目背景；2. 核心痛点；3. 建模目标；4. 总体架构；5. 动态通信图；6. 外层状态机；7. 内层状态机；8. 分层参数；9. 离散事件仿真；10. 模拟实验设计流程；11. 输出指标；12. 验证方案；13. 创新点；14. 应用价值；15. 总结与展望。
|
||||
|
||||
# 结论
|
||||
|
||||
本项目以 Agent 的业务行为作为网络流量产生机制，用双层随机状态机连接“任务执行”和“消息传播”，再结合队列、拓扑和离散事件仿真形成可解释、可校准、可扩展的流量预测框架。方案既能服务比赛中的数学建模与仿真验证，也具有容量规划、架构优化和故障预警等工程价值。
|
||||
@@ -0,0 +1,642 @@
|
||||
---
|
||||
title: "大规模多智能体网络流量建模方案"
|
||||
subtitle: "基于双层随机混合自动机的离散事件仿真"
|
||||
author: "参赛团队：待填写"
|
||||
date: "2026年8月"
|
||||
toc: true
|
||||
toc-title: "目录"
|
||||
number-sections: true
|
||||
---
|
||||
|
||||
# 本次修订说明
|
||||
|
||||
**修订日期：2026年8月13日**
|
||||
|
||||
本版本补充了基于大模型模拟数据开展快速实验的技术方案，主要改动如下：
|
||||
|
||||
- 在“参数估计与数据方案”章节新增 **7.4 模拟实验设计流程（基于大模型）**；
|
||||
- 定义任务行为画像向量，包括工具调用概率、任务拆分概率、平均子任务数、超时与失败概率、处理时间和消息大小参数；
|
||||
- 说明采用“大模型生成行为画像 + 本地受约束随机引擎生成事件日志”的混合方法，而不是让大模型直接逐行生成海量日志；
|
||||
- 补充 `task_id`、`message_id` 和 `parent_message_id` 驱动的消息因果链构造方法；
|
||||
- 增加概率范围、正值参数、事件时间顺序、消息守恒、训练/验证/测试隔离和随机种子等质量约束；
|
||||
- 补充静态均值基线、无上下文模型、完整双层状态机模型、压力实验和重试放大实验的闭环；
|
||||
- 明确模拟数据的用途是验证模型实现和实验方法，正式结论仍需真实日志或可控 Agent 实验校准。
|
||||
|
||||
上述流程已在 `agent_traffic_experiments/` 中实现，模型输入输出字段和本方案中的状态机、参数估计及评估指标保持对应。
|
||||
|
||||
# 摘要
|
||||
|
||||
本文面向大规模多智能体系统中的通信流量预测问题，建立由动态通信图、双层随机混合自动机、消息队列、路由与目标选择模型、离散事件调度器和流量统计模型组成的统一框架。外层自动机描述消息在节点之间的传播位置和交互路径，内层自动机描述节点接收、排队、思考、任务拆分、工具调用、等待、重试和发送等行为。模型通过节点能力、任务上下文、局部拓扑及系统负载共同决定状态转移概率、状态持续时间、输出消息数量和消息大小。
|
||||
|
||||
参数主要由小规模运行日志、系统配置和压力测试数据估计；对于新任务、新阶段和新节点，采用分层参数共享、特征表示和回退机制实现组合泛化。最终利用离散事件仿真，计算节点与链路流量、任务时延、吞吐量、队列长度、流量放大系数以及故障重试效应，为大规模 Agent 网络的容量规划和架构优化提供依据。
|
||||
|
||||
**关键词：** 多智能体系统；网络流量；随机混合自动机；离散事件仿真；排队模型；分层参数
|
||||
|
||||
# 1 问题定义
|
||||
|
||||
## 1.1 研究对象
|
||||
|
||||
研究对象为由 Agent、工具服务、数据库、模型服务等计算与通信实体构成的异构网络。外部任务进入网络后，节点会根据任务阶段和自身能力进行推理、拆分、协作、查询、转发或返回结果，并产生新的内部消息。
|
||||
|
||||
系统需要根据有限规模日志和配置参数，预测更大规模或更高负载条件下的网络行为。
|
||||
|
||||
## 1.2 输入
|
||||
|
||||
模型输入包括：
|
||||
|
||||
- 网络拓扑及其动态变化规则；
|
||||
- 节点能力、并发上限、服务速度和队列容量；
|
||||
- 外部任务类型、阶段、到达过程和优先级；
|
||||
- 状态转移、状态持续时间和下游消息数量参数；
|
||||
- 不同消息类型的大小分布；
|
||||
- 链路带宽、传播时延和传输失败参数；
|
||||
- 超时阈值、最大重试次数和退避策略。
|
||||
|
||||
## 1.3 输出
|
||||
|
||||
在时间窗口 $T$ 内，输出包括：
|
||||
|
||||
1. 节点入站/出站消息数和字节数；
|
||||
2. 链路累计流量、平均速率和利用率；
|
||||
3. 任务完成时间及平均、P95、P99 延迟；
|
||||
4. 节点队列长度、利用率、吞吐量和丢弃数；
|
||||
5. 平均跳数、内部消息数和流量放大系数；
|
||||
6. 超时率、失败率、重试次数和故障影响范围；
|
||||
7. 热点节点、瓶颈链路和系统稳定区间。
|
||||
|
||||
## 1.4 建模边界
|
||||
|
||||
本模型主要描述应用层消息及其引发的计算、排队和路由行为。若比赛数据只提供逻辑消息大小，则不额外精确建模 TCP/IP 包头、分片和底层重传；如能获得网络层数据，可在逻辑消息大小之上增加协议开销系数。
|
||||
|
||||
# 2 基本假设
|
||||
|
||||
为构建可计算模型，作如下基础假设：
|
||||
|
||||
1. 系统可表示为随时间变化的有向图，节点和链路属性在事件发生时更新；
|
||||
2. 消息是仿真的基本通信对象，每条消息具有来源、目的、类型、大小和任务关联；
|
||||
3. 节点共享通用状态集合，但可执行动作和参数因能力、上下文与负载不同；
|
||||
4. 状态持续时间和消息大小服从从日志估计的经验分布或参数分布；
|
||||
5. 外部任务到达可按实测时间序列重放；无日志时，基线场景采用泊松或非齐次泊松过程；
|
||||
6. 节点处理资源和链路带宽有限，负载超过容量会形成队列或丢弃；
|
||||
7. 超时与失败可触发有限重试，重试策略由最大次数和退避规则控制；
|
||||
8. 不同随机实验使用独立随机种子，并通过多次重复估计均值和置信区间。
|
||||
|
||||
# 3 系统对象与符号定义
|
||||
|
||||
## 3.1 动态通信图
|
||||
|
||||
系统在时刻 $t$ 表示为：
|
||||
|
||||
$$
|
||||
G(t)=(V(t),E(t))
|
||||
$$
|
||||
|
||||
$V(t)$ 为节点集合，$E(t)$ 为有向通信边集合。对链路 $e=(u,v)$，定义：
|
||||
|
||||
$$
|
||||
g_e(t)=(C_e,d_e,u_e(t),p_e^{fail})
|
||||
$$
|
||||
|
||||
其中 $C_e$ 为带宽，$d_e$ 为基础传播时延，$u_e(t)$ 为利用率，$p_e^{fail}$ 为传输失败概率。
|
||||
|
||||
## 3.2 节点
|
||||
|
||||
节点 $v$ 表示为：
|
||||
|
||||
$$
|
||||
v=(x_v,q_v,G_v,z_v,r_v,Q_v)
|
||||
$$
|
||||
|
||||
其中：
|
||||
|
||||
- $x_v$：能力和静态资源向量；
|
||||
- $q_v$：节点级资源状态，取 `Idle`、`Busy`、`Saturated` 或 `Failed`，不表示某条消息所处的业务处理阶段；
|
||||
- $G_v$：局部拓扑子图；
|
||||
- $z_v$：从局部拓扑提取的度数、距离、邻居能力和负载特征；
|
||||
- $r_v$：并发数、处理资源占用及可用容量；
|
||||
- $Q_v$：等待队列。
|
||||
|
||||
能力向量示例：
|
||||
|
||||
```text
|
||||
x_v = {
|
||||
can_reason: true,
|
||||
can_split_task: true,
|
||||
can_call_tool: true,
|
||||
can_query_database: false,
|
||||
can_forward: true,
|
||||
max_concurrency: 4
|
||||
}
|
||||
```
|
||||
|
||||
## 3.3 消息
|
||||
|
||||
消息定义为：
|
||||
|
||||
$$
|
||||
m=(message\_id,task\_id,parent\_message\_id,correlation\_id,
|
||||
attempt\_id,source,destination,next\_hop,message\_type,
|
||||
message\_size,priority,path,h,retry\_count,t_{create})
|
||||
$$
|
||||
|
||||
其中 `destination` 是逻辑最终接收节点，`next_hop` 是本次传输实际到达的下一跳；$h$ 是消息已完成的跳数。`parent_message_id` 用于还原消息触发关系，`task_id` 用于关联同一次任务，`correlation_id` 用于匹配请求、响应、错误和超时，`attempt_id` 用于区分同一逻辑请求的不同发送尝试。
|
||||
|
||||
## 3.4 任务上下文
|
||||
|
||||
任务上下文 $c$ 包含任务类型、任务阶段、复杂度、可靠性要求、实时性要求等。为了支持未知类别，除离散标签外，还可使用如下可解释特征：
|
||||
|
||||
```text
|
||||
long_context, needs_external_tool, collaboration_degree,
|
||||
realtime_requirement, reliability_requirement, result_complexity
|
||||
```
|
||||
|
||||
# 4 双层随机混合自动机
|
||||
|
||||
## 4.1 外层自动机
|
||||
|
||||
外层自动机描述消息的网络位置和交互关系。外层状态可写为：
|
||||
|
||||
$$
|
||||
S_m^{outer}(t)=(v_t,path_m,h_m,c_m)
|
||||
$$
|
||||
|
||||
当节点内部状态转移生成新消息时，外层模型选择目标节点或下一跳，并计算传输完成时间。目标选择模型为：
|
||||
|
||||
$$
|
||||
P(dst=u\mid v,type,c,z_v,\ell)=
|
||||
\frac{\exp(r_u)}{\sum_{k\in\mathcal N_v^{feasible}}\exp(r_k)}
|
||||
$$
|
||||
|
||||
评分 $r_u$ 可以综合能力匹配、跳数、队列长度、链路利用率和历史成功率：
|
||||
|
||||
$$
|
||||
r_u=\theta_1 match_u-\theta_2 distance_u-\theta_3 queue_u
|
||||
-\theta_4 utilization_{vu}+\theta_5 reliability_u
|
||||
$$
|
||||
|
||||
## 4.2 内层自动机
|
||||
|
||||
节点内部状态集合定义为：
|
||||
|
||||
$$
|
||||
\mathcal Q=\{Idle,Receive,Queue,Think,Split,CallAgent,
|
||||
CallTool,Query,Forward,Wait,Retry,Send,Failed\}
|
||||
$$
|
||||
|
||||
该集合表示消息或任务处理上下文状态 $q_m$，不是节点整体资源状态 $q_v$。同一节点可同时维护多个 $q_m$，其数量和资源占用由 $r_v$ 与 `max_concurrency` 约束。
|
||||
|
||||
主要状态转移如下：
|
||||
|
||||
```text
|
||||
Idle → Receive
|
||||
Receive → Queue / Think
|
||||
Queue → Think
|
||||
Think → Send / Split / CallAgent / CallTool / Query / Forward
|
||||
Split / CallAgent / CallTool / Query / Forward → Wait
|
||||
Wait → Think / Retry
|
||||
Retry → Think / Failed
|
||||
Send / Failed → Idle
|
||||
```
|
||||
|
||||
每次状态转移可同时产生状态持续时间、输出消息集合和流量增量。因此，模型属于含离散状态、连续时间和随机输出的混合自动机。
|
||||
|
||||
## 4.3 可行转移过滤
|
||||
|
||||
设状态 $q$ 的候选动作集合为 $\mathcal A(q)$，根据能力、拓扑和资源得到可行集合：
|
||||
|
||||
$$
|
||||
\mathcal A(X)=\{a\in\mathcal A(q):constraint(a,x_v,z_v,r_v,c)=1\}
|
||||
$$
|
||||
|
||||
例如：
|
||||
|
||||
- `can_call_tool=false` 时移除 `CallTool`；
|
||||
- 无可用数据服务时移除 `Query`；
|
||||
- 队列或并发已满时进入等待、拒绝或转发分支；
|
||||
- 达到最大重试次数后移除继续重试分支。
|
||||
|
||||
## 4.4 条件状态转移概率
|
||||
|
||||
对于可行转移 $j$，定义评分：
|
||||
|
||||
$$
|
||||
s_j=\beta_j+\alpha_{task,j}+\gamma_{phase,j}
|
||||
+\eta_{cap,j}+\delta_{topology,j}+\rho_{load,j}
|
||||
$$
|
||||
|
||||
通过 softmax 得到：
|
||||
|
||||
$$
|
||||
P(j\mid X)=\frac{e^{s_j}}
|
||||
{\sum_{k\in\mathcal A(X)}e^{s_k}}
|
||||
$$
|
||||
|
||||
若日志样本较少，可采用带平滑的频率估计作为初始值：
|
||||
|
||||
$$
|
||||
\hat P_{ij}=\frac{N_{ij}+\alpha}{\sum_k N_{ik}+K\alpha}
|
||||
$$
|
||||
|
||||
其中 $\alpha$ 为平滑系数，$K$ 为候选转移数量。
|
||||
|
||||
## 4.5 状态持续时间
|
||||
|
||||
不同状态采用不同持续时间分布。正值且右偏的数据可使用对数正态分布：
|
||||
|
||||
$$
|
||||
\log T_q\sim \mathcal N(
|
||||
\mu_q+\alpha_{task}+\gamma_{phase}+\eta_v+\rho_{load},\sigma_q^2)
|
||||
$$
|
||||
|
||||
当样本量充足时，优先保存经验累积分布，并报告均值、中位数、P95 和 P99，避免只使用平均值掩盖长尾。
|
||||
|
||||
## 4.6 输出消息模型
|
||||
|
||||
一次转移产生的消息数量为 $N_{out}$，消息集合为：
|
||||
|
||||
$$
|
||||
M_{out}=\{m_1,m_2,\ldots,m_{N_{out}}\}
|
||||
$$
|
||||
|
||||
任务拆分的 $N_{out}$ 可采用经验离散分布或泊松、负二项分布。消息大小按类型和阶段建模：
|
||||
|
||||
$$
|
||||
\log S_m\sim\mathcal N(\mu_{type,phase},\sigma_{type,phase}^2)
|
||||
$$
|
||||
|
||||
# 5 队列、链路与时间模型
|
||||
|
||||
## 5.1 节点队列
|
||||
|
||||
节点 $v$ 在时间窗口内的队列动态为：
|
||||
|
||||
$$
|
||||
Q_v(t+\Delta t)=\min\left\{Q_v^{max},
|
||||
\max[0,Q_v(t)+A_v(t)-D_v(t)]\right\}
|
||||
$$
|
||||
|
||||
当队列达到 $Q_v^{max}$ 时，根据系统策略执行丢弃、拒绝、限流或改道。
|
||||
|
||||
$Q_v(t)$ 仅包含已经到达节点但尚未分配到活跃处理资源的消息；$D_v(t)$ 表示窗口内从等待队列取出并开始处理的消息数。队列采用有界、按 `priority` 优先且同优先级按到达顺序处理的规则。默认 `Wait` 上下文仍占用并发槽；实际系统若在等待期间释放资源，应设置 `wait_holds_slot=false`，并在响应到达后重新申请并发槽。
|
||||
|
||||
若某基线场景满足泊松到达和指数服务，可用 M/M/1 结果进行理论校验：
|
||||
|
||||
$$
|
||||
\rho=\frac{\lambda}{\mu},\qquad
|
||||
W=\frac{1}{\mu-\lambda},\qquad \lambda<\mu
|
||||
$$
|
||||
|
||||
正式仿真不强制要求指数分布，可直接使用经验处理时间和多并发服务资源。
|
||||
|
||||
## 5.2 链路传输时间
|
||||
|
||||
消息 $m$ 经过链路 $e$ 的基础传输时间为：
|
||||
|
||||
$$
|
||||
T_{e,m}=d_e+\frac{S_m}{C_e}+T_e^{queue}
|
||||
$$
|
||||
|
||||
如需更细致地表达利用率导致的非线性排队，可设：
|
||||
|
||||
$$
|
||||
T_e^{queue}=\kappa_e\frac{u_e}{1-u_e+\varepsilon}
|
||||
$$
|
||||
|
||||
该形式需要通过压力测试校准，不应在无数据时声称为真实网络规律。
|
||||
|
||||
## 5.3 超时和重试
|
||||
|
||||
请求在超时阈值 $T_{timeout}$ 前未收到有效响应时进入 `Retry`。若单次成功概率为 $1-p$，允许最多 $R$ 次重试，则理论期望请求次数为：
|
||||
|
||||
$$
|
||||
E[N_{request}]=\sum_{k=0}^{R}p^k=
|
||||
\frac{1-p^{R+1}}{1-p}
|
||||
$$
|
||||
|
||||
超时概率本身可以随队列和链路利用率变化：
|
||||
|
||||
$$
|
||||
logit(p_{timeout})=omega_0+omega_1 Q_v+omega_2 u_e+omega_3 T_{service}
|
||||
$$
|
||||
|
||||
# 6 流量与性能指标
|
||||
|
||||
## 6.1 节点流量
|
||||
|
||||
时间窗口 $T$ 内节点入站和出站字节数：
|
||||
|
||||
$$
|
||||
B_v^{in}(T)=\sum_{m:dst(m)=v}S_m,
|
||||
\qquad
|
||||
B_v^{out}(T)=\sum_{m:src(m)=v}S_m
|
||||
$$
|
||||
|
||||
对应平均速率为 $B/T$。
|
||||
|
||||
## 6.2 链路流量
|
||||
|
||||
$$
|
||||
B_e(T)=\sum_{m:e\in path(m)}S_m,
|
||||
\qquad
|
||||
R_e(T)=\frac{B_e(T)}{T}
|
||||
$$
|
||||
|
||||
链路利用率为：
|
||||
|
||||
$$
|
||||
U_e(T)=\frac{R_e(T)}{C_e}
|
||||
$$
|
||||
|
||||
## 6.3 任务级指标
|
||||
|
||||
任务 $i$ 的端到端延迟：
|
||||
|
||||
$$
|
||||
L_i=t_i^{finish}-t_i^{arrival}
|
||||
$$
|
||||
|
||||
任务内部流量放大系数定义为：
|
||||
|
||||
$$
|
||||
AF_i=\frac{\text{任务 }i\text{ 产生的内部总字节数}}
|
||||
{\text{任务 }i\text{ 的外部输入字节数}}
|
||||
$$
|
||||
|
||||
也可分别计算消息数量放大系数、工具调用放大系数和重试放大系数。
|
||||
|
||||
## 6.4 系统稳定性
|
||||
|
||||
对每个节点检查有效到达率与服务能力：
|
||||
|
||||
$$
|
||||
\rho_v=\frac{\lambda_v^{eff}}{\mu_v}
|
||||
$$
|
||||
|
||||
其中 $\mu_v$ 按基准模型定义为节点的总单位时间处理能力，已经综合节点并发槽、资源竞争和消息类型差异，不能再默认乘以 `max_concurrency`。若实测参数是单槽服务率，则必须先根据并发竞争和资源共享关系换算为节点总处理能力。多个关键节点长期满足 $\rho_v\ge 1$ 时，系统通常进入队列持续增长区间。由于任务拆分和重试会改变 $\lambda_v^{eff}$，稳定性需要通过迭代或仿真而非只看外部到达率判断。
|
||||
|
||||
# 7 参数估计与数据方案
|
||||
|
||||
## 7.1 日志模式
|
||||
|
||||
每条事件至少包含：
|
||||
|
||||
| 字段 | 含义 |
|
||||
|---|---|
|
||||
| timestamp | 事件时间 |
|
||||
| task_id、message_id、parent_message_id | 任务与消息触发关系 |
|
||||
| correlation_id、attempt_id | 请求响应匹配与重试尝试区分 |
|
||||
| source、destination、next_hop | 逻辑发送端、逻辑接收端与实际下一跳 |
|
||||
| task_type、task_phase、message_type | 业务上下文 |
|
||||
| state_before、state_after | 状态转移 |
|
||||
| state_duration | 状态持续时间 |
|
||||
| message_size | 消息字节数 |
|
||||
| queue_length、concurrency | 节点负载 |
|
||||
| link_utilization | 链路负载 |
|
||||
| success、retry_count | 结果与重试 |
|
||||
|
||||
## 7.2 估计流程
|
||||
|
||||
1. 根据 task_id 和 parent_message_id 还原任务调用树；
|
||||
2. 校验时间戳顺序、重复消息和缺失字段；
|
||||
3. 按状态、任务、阶段、能力和负载分组；
|
||||
4. 估计转移概率、持续时间和消息大小分布；
|
||||
5. 使用压力测试估计高负载下的服务率和超时率；
|
||||
6. 划分训练集、验证集和测试集；
|
||||
7. 记录每个参数的样本量、来源、版本和置信度。
|
||||
|
||||
## 7.3 未知类别与回退
|
||||
|
||||
运行时依次尝试：
|
||||
|
||||
```text
|
||||
类别专属参数
|
||||
→ 相似类别或特征组合参数
|
||||
→ 同任务类型的上级参数
|
||||
→ 全局状态基础参数
|
||||
```
|
||||
|
||||
回退结果应附带 `parameter_source=fallback` 和较低置信度，避免把缺少数据的预测解释为高可信结论。
|
||||
|
||||
## 7.4 模拟实验设计流程（基于大模型）
|
||||
|
||||
在尚未获得足量真实 Agent 运行日志时，采用“大模型生成行为画像 + 规则约束生成事件日志”的混合数据构造方法。大模型用于提供不同任务类型的语义差异和合理参数组合，本地生成程序负责生成大规模、结构一致且可重复的日志。
|
||||
|
||||
### 7.4.1 流程设计
|
||||
|
||||
```text
|
||||
步骤1：定义任务类型、网络节点和实验负载
|
||||
↓
|
||||
步骤2：大模型生成任务行为画像
|
||||
↓
|
||||
步骤3：执行结构与数值约束校验
|
||||
↓
|
||||
步骤4：本地生成器扩展任务、状态和消息事件
|
||||
↓
|
||||
步骤5：按任务划分训练集、验证集与测试集
|
||||
↓
|
||||
步骤6：训练集估计状态机和分布参数
|
||||
↓
|
||||
步骤7：验证集选择分布和调整参数
|
||||
↓
|
||||
步骤8：测试集作为模拟实测值进行最终预测验证
|
||||
↓
|
||||
步骤9：执行基线、压力和重试实验并输出图表
|
||||
```
|
||||
|
||||
大模型生成的单个行为画像包括：
|
||||
|
||||
$$
|
||||
profile=(p_{tool},p_{split},E[N_{subtask}],p_{timeout},p_{fail},
|
||||
\mu_T,CV_T,\mu_{req},\mu_{resp},CV_S)
|
||||
$$
|
||||
|
||||
分别表示工具调用概率、任务拆分概率、平均子任务数、超时概率、失败概率、处理时间均值和变异系数、请求与响应消息大小均值以及消息大小变异系数。
|
||||
|
||||
### 7.4.2 结构化事件扩展
|
||||
|
||||
行为画像通过本地随机引擎扩展为事件日志。每个任务生成唯一 `task_id`，每条消息生成唯一 `message_id`，并通过 `parent_message_id` 记录任务拆分、工具请求和返回结果之间的因果关系。生成器按照状态机约束生成：
|
||||
|
||||
```text
|
||||
外部任务到达 → 协调节点思考 → 拆分或调用执行节点
|
||||
→ 可选工具调用 → 超时与有限重试 → 执行结果返回
|
||||
→ 协调节点汇总 → 最终响应
|
||||
```
|
||||
|
||||
生成过程中同时维护时间戳、状态持续时间、消息大小、来源节点、目标节点、队列长度、成功状态和重试次数。
|
||||
|
||||
### 7.4.3 数据质量约束
|
||||
|
||||
- 概率参数限制在 $[0,0.95]$，不可行状态转移概率设为零；
|
||||
- 子任务数量、消息大小和处理时间必须为正，并设置合理上限；
|
||||
- 消息标识唯一，父消息必须存在或为空；
|
||||
- 同一任务的事件时间保持因果顺序；
|
||||
- 发送、接收、在途、丢弃和外部输出之间满足消息守恒；
|
||||
- 训练集、验证集和测试集按完整任务划分，避免消息级数据泄漏；
|
||||
- 保存生成模型、提示词版本、配置文件和随机种子。
|
||||
|
||||
### 7.4.4 实验闭环
|
||||
|
||||
训练事件用于估计状态转移概率、持续时间分布、消息大小分布和重试参数；验证事件用于选择分布和调整参数；测试事件只按任务聚合为模拟实测值并用于最终评估。随后分别运行静态均值基线、无任务上下文模型和完整双层状态机模型，并比较内部流量、任务延迟、消息数、工具调用数和流量放大系数。压力实验通过提高外部到达率观察队列和容量拐点，重试实验通过组合超时概率与最大重试次数观察成功率和流量放大。
|
||||
|
||||
该流程的定位是快速验证模型实现、实验方法和指标体系。模拟数据不得表述为真实生产数据；正式结论仍需真实日志或可控 Agent 实验进行校准。
|
||||
|
||||
# 8 离散事件仿真算法
|
||||
|
||||
## 8.1 事件类型
|
||||
|
||||
- ExternalArrival：外部任务到达；
|
||||
- MessageArrival：消息抵达目标节点；
|
||||
- ServiceStart：节点获得处理资源；
|
||||
- StateComplete：状态处理完成；
|
||||
- TransmissionComplete：消息传输完成；
|
||||
- ResponseArrival：协作或工具结果返回；
|
||||
- Timeout：请求超时；
|
||||
- Retry：重新发送或改选目标；
|
||||
- Failure/Recovery：节点或链路故障与恢复；
|
||||
- Snapshot：周期性统计快照。
|
||||
|
||||
## 8.2 核心状态
|
||||
|
||||
仿真器维护：全局时钟、优先事件队列、节点状态、节点等待队列、链路状态、未完成请求表、任务状态表以及流量统计器。
|
||||
|
||||
## 8.3 核心伪代码
|
||||
|
||||
```text
|
||||
初始化拓扑、节点、参数和随机种子
|
||||
生成外部任务到达事件
|
||||
|
||||
while 事件队列非空 且 当前时间 < 仿真终止时间:
|
||||
event = 弹出时间最早的事件
|
||||
clock = event.time
|
||||
|
||||
if event 为消息到达:
|
||||
更新目标节点入站流量
|
||||
若有处理资源则安排处理，否则进入队列
|
||||
|
||||
if event 为状态完成:
|
||||
读取任务、阶段、能力、拓扑和负载
|
||||
过滤不可行转移
|
||||
计算条件概率并抽样下一状态
|
||||
抽样持续时间、输出消息数量和消息大小
|
||||
更新节点状态、队列和资源
|
||||
为输出消息选择目标并安排传输事件
|
||||
必要时安排超时事件
|
||||
|
||||
if event 为响应或超时:
|
||||
取消互斥事件或触发重试/失败
|
||||
|
||||
更新任务、节点、链路和全局指标
|
||||
```
|
||||
|
||||
## 8.4 事件冲突处理
|
||||
|
||||
响应和超时可能同时存在于事件队列。为每个请求维护唯一 `request_id` 和状态标记；先发生的有效事件更新请求状态，后续互斥事件到达时被忽略，防止同一请求既成功又重试。
|
||||
|
||||
## 8.5 可复现性
|
||||
|
||||
所有随机源由统一种子管理。实验配置保存为版本化文件，包含拓扑、参数、仿真时长、预热期、重复次数和种子列表。报告中的每张图应能由对应配置和脚本重新生成。
|
||||
|
||||
# 9 大规模仿真优化
|
||||
|
||||
## 9.1 事件驱动
|
||||
|
||||
不按固定毫秒更新所有节点，只处理实际事件，复杂度主要与事件数量有关。若总事件数为 $M$，二叉堆优先队列的调度复杂度约为 $O(M\log M)$。
|
||||
|
||||
## 9.2 稀疏拓扑与局部查询
|
||||
|
||||
采用邻接表存储通信图，节点选择只遍历可行邻居，避免建立 $|V|^2$ 的全连接矩阵。
|
||||
|
||||
## 9.3 节点聚合
|
||||
|
||||
对于能力、参数和连接模式相同的大量节点，可在宏观实验中按节点群组聚合；在需要尾延迟和热点分析的局部区域保留细粒度仿真。
|
||||
|
||||
## 9.4 分区与并行
|
||||
|
||||
可按网络社区或业务域进行分区，跨区消息作为边界事件交换。并行化时必须保证事件因果顺序，比赛原型阶段可先完成单机确定性版本，再扩展并行实现。
|
||||
|
||||
# 10 三节点算例
|
||||
|
||||
设外部任务大小为 2 KB，路径为：
|
||||
|
||||
```text
|
||||
外部 → Node_A → Node_B → Node_C → Node_B → Node_A
|
||||
```
|
||||
|
||||
其中：
|
||||
|
||||
- A→B 任务请求 3 KB；
|
||||
- B→C 工具请求 1 KB；
|
||||
- C→B 工具响应 4 KB；
|
||||
- B→A 最终结果 2 KB；
|
||||
- B 调用工具的基础概率为 0.7。
|
||||
|
||||
若一次任务实际进入工具调用分支，则节点间链路累计流量为：
|
||||
|
||||
$$
|
||||
B_{AB}=3+2=5\text{ KB}
|
||||
$$
|
||||
|
||||
$$
|
||||
B_{BC}=1+4=5\text{ KB}
|
||||
$$
|
||||
|
||||
若外部任务到达率为每秒 100 条，忽略排队和失败，则期望链路流量近似为：
|
||||
|
||||
$$
|
||||
R_{AB}=100\times5=500\text{ KB/s}
|
||||
$$
|
||||
|
||||
$$
|
||||
R_{BC}=100\times0.7\times5=350\text{ KB/s}
|
||||
$$
|
||||
|
||||
该算例用于验证计数和事件实现。正式实验将引入随机消息大小、处理时间、队列、有限带宽和超时重试。
|
||||
|
||||
# 11 验证设计概述
|
||||
|
||||
模型验证分为：
|
||||
|
||||
1. 手工算例逐事件对账；
|
||||
2. 小规模日志训练/验证/测试集预测；
|
||||
3. 与静态倍数、纯拓扑和 M/M/1 基线比较；
|
||||
4. 移除分层阶段、局部拓扑、队列或重试模块的消融实验；
|
||||
5. 到达率、带宽、并发数、超时率和重试上限敏感性分析；
|
||||
6. 10—100000 仿真节点的性能扩展实验。
|
||||
|
||||
预测误差使用 MAE、RMSE 和 MAPE；尾延迟单独比较 P95/P99；热点识别使用 Precision、Recall 和 F1；仿真性能报告运行时间、内存峰值和每秒处理事件数。
|
||||
|
||||
# 12 模型局限与改进方向
|
||||
|
||||
- 小规模日志不能直接覆盖大规模系统中的新拥塞机制，需要压力实验校准；
|
||||
- 泊松到达只适合作为无实测数据时的基线，突发任务应使用实测序列或批量到达模型；
|
||||
- 参数之间可能存在相关性，独立抽样会低估极端事件，后续可引入联合分布或条件生成模型；
|
||||
- 若新能力引入流式通信、广播或长期连接，需要扩展状态机结构；
|
||||
- 超大规模精细仿真计算成本较高，可研究多分辨率和代理模型加速；
|
||||
- 模型预测代表给定假设和参数下的仿真结果，必须同步报告参数来源和置信度。
|
||||
|
||||
# 13 最终模型定义
|
||||
|
||||
消息处理事件在时刻 $t$ 的完整状态表示为：
|
||||
|
||||
$$
|
||||
s_m(t)=(v,q_v,q_m,x_v,z_v,c,m,path,h,Q_v(t),r_v,\tau_v,retry\_count)
|
||||
$$
|
||||
|
||||
一次状态更新为：
|
||||
|
||||
$$
|
||||
(s_{t+\Delta t},M_{out},\Delta F)=f(s_t,g_e(t),\xi_t)
|
||||
$$
|
||||
|
||||
其中 $\xi_t$ 表示状态选择、持续时间、消息大小、目标选择和故障等随机变量，$\Delta F$ 表示节点及链路流量增量。
|
||||
|
||||
因此，整体模型可概括为：
|
||||
|
||||
$$
|
||||
\boxed{\text{随机混合自动机}+\text{消息队列}+\text{动态通信图}
|
||||
+\text{事件调度器}+\text{路由模型}+\text{流量统计}}
|
||||
$$
|
||||
|
||||
# 结论
|
||||
|
||||
本方案将 Agent 的任务行为转化为可观测、可估计的消息生成机制，并通过双层状态机与动态网络连接起来。模型既保留状态、路径、参数和流量之间的可解释关系，又能通过事件仿真表达队列、拥塞、超时和重试的非线性反馈。下一阶段应以最小可运行仿真器和标准化实验为重点，用数据检验模型精度、模块必要性和大规模运行能力。
|
||||
@@ -0,0 +1,554 @@
|
||||
---
|
||||
title: "大规模多智能体网络流量模型"
|
||||
subtitle: "验证与评估实验计划（待执行）"
|
||||
author: "参赛团队：待填写"
|
||||
date: "2026年8月"
|
||||
toc: true
|
||||
toc-title: "目录"
|
||||
number-sections: true
|
||||
---
|
||||
|
||||
# 本次修订说明
|
||||
|
||||
**修订日期：2026年8月13日**
|
||||
|
||||
本版本在实验总体框架中加入了可立即执行的模拟实验方案，主要改动如下：
|
||||
|
||||
- 在“验证总体框架”后新增 **1.3 模拟实验设计流程**；
|
||||
- 将模拟过程拆分为场景定义、LLM 行为画像生成、画像校验、结构化日志生成、训练/验证/测试隔离、参数估计、快速实验和结果输出八个环节；
|
||||
- 设置简单问答、工具研究和多 Agent 协作分析三类初始任务场景；
|
||||
- 规定 LLM 输出固定 JSON 画像，并在缺少 API Key 或请求失败时使用版本化本地画像回退；
|
||||
- 明确训练集用于估计参数、验证集用于选择分布和调整参数、测试集只用于最终评估，避免任务级数据泄漏；
|
||||
- 增加预测验证、模型基线、到达率压力和超时重试四类快速实验的输入输出说明；
|
||||
- 规定保存原始事件 CSV、行为画像 JSON、估计参数 JSON、实验结果 CSV、图表、配置文件和随机种子；
|
||||
- 强调最终报告必须把模拟结果标注为“模拟数据”，获得真实日志后使用同一实验管线重新验证。
|
||||
|
||||
配套实验工程位于 `agent_traffic_experiments/`，当前已经能够自动生成数据并输出预测对比图、压力曲线和重试流量放大热力图。
|
||||
|
||||
# 文档说明
|
||||
|
||||
本文是验证与评估报告的前置计划，不包含尚未实际获得的准确率、性能或显著性结论。实验执行后，应将本计划中的“预期图表、数据表和验收标准”替换或补充为真实结果，并保留失败实验和误差解释。
|
||||
|
||||
实验目标是回答四个问题：
|
||||
|
||||
1. 仿真程序是否正确实现了数学模型？
|
||||
2. 模型能否预测真实或半真实 Agent 网络的流量与延迟？
|
||||
3. 双层状态机、队列、拓扑和重试模块是否确有必要？
|
||||
4. 模型能否在更大规模网络中保持可接受的运行开销与稳定性？
|
||||
|
||||
# 1 验证总体框架
|
||||
|
||||
## 1.1 验证层次
|
||||
|
||||
| 层次 | 核心问题 | 主要方法 | 输出 |
|
||||
|---|---|---|---|
|
||||
| V1 实现正确性 | 事件、消息和流量是否算对 | 手工算例、单元测试、守恒检查 | 对账表 |
|
||||
| V2 参数可信度 | 参数是否由日志稳定估计 | 分布拟合、Bootstrap、训练/验证/测试划分 | 参数表与区间 |
|
||||
| V3 预测准确性 | 能否预测测试场景 | 实测或重放对比 | 误差指标与拟合图 |
|
||||
| V4 模型有效性 | 完整模型是否优于简化模型 | 基线和消融实验 | 对比表 |
|
||||
| V5 鲁棒与扩展性 | 高负载、故障和大规模下表现如何 | 压力、故障、敏感性和规模实验 | 容量与性能曲线 |
|
||||
|
||||
## 1.2 实验原则
|
||||
|
||||
- 所有实验配置、随机种子和软件版本可追踪；
|
||||
- 训练数据不得进入测试集；
|
||||
- 每个随机场景至少重复多次，并报告均值和 95% 置信区间；
|
||||
- 真实数据、合成数据和假设参数必须清楚标注；
|
||||
- 不仅报告平均值，还报告 P95、P99 和最差场景；
|
||||
- 不删除对模型不利的异常结果，应分析其原因和适用边界。
|
||||
|
||||
## 1.3 模拟实验设计流程
|
||||
|
||||
在真实日志尚不足以覆盖全部任务类型、网络规模和故障条件时，先通过受约束的大模型模拟构建实验数据，快速验证模型与代码闭环。流程如下。
|
||||
|
||||
```text
|
||||
任务与场景设计
|
||||
↓
|
||||
LLM生成行为画像
|
||||
↓
|
||||
画像合法性校验与默认参数回退
|
||||
↓
|
||||
本地随机引擎扩展结构化事件日志
|
||||
↓
|
||||
按任务划分训练集 / 验证集 / 测试集
|
||||
↓
|
||||
训练集估计状态机参数
|
||||
↓
|
||||
验证集选择分布和调整参数
|
||||
↓
|
||||
测试集聚合为模拟实测值
|
||||
↓
|
||||
完整模型、无上下文模型、静态均值基线对比
|
||||
↓
|
||||
压力实验与重试放大实验
|
||||
↓
|
||||
自动输出数据表、参数文件、指标和图表
|
||||
```
|
||||
|
||||
### 1.3.1 第一步：定义模拟场景
|
||||
|
||||
首轮至少设置三类具有复杂度梯度的任务：
|
||||
|
||||
| 任务类型 | 主要特点 | 预期通信行为 |
|
||||
|---|---|---|
|
||||
| 简单问答 | 单节点推理为主 | 消息少、时延短、很少调用工具 |
|
||||
| 工具研究 | 需要搜索或数据查询 | 工具调用率高、响应消息较大 |
|
||||
| 多 Agent 协作分析 | 任务拆分和结果汇总 | 子任务多、路径长、队列和重试影响明显 |
|
||||
|
||||
同时定义 Agent 数量、工具数量、并发容量、队列容量、链路带宽和基础时延。
|
||||
|
||||
### 1.3.2 第二步：LLM生成行为画像
|
||||
|
||||
大模型不直接输出海量日志，而是为每类任务生成有限的行为参数：工具调用概率、拆分概率、平均子任务数、处理时间、请求/响应大小、超时率和失败率。输出必须采用固定 JSON 字段，并经过范围检查。
|
||||
|
||||
若没有 API Key 或模型调用失败，使用版本化的内置画像回退，以保证实验可离线复现；报告中记录本次实际使用的是 LLM 画像还是本地回退画像。
|
||||
|
||||
### 1.3.3 第三步：生成结构化日志
|
||||
|
||||
本地程序根据画像运行受约束的随机状态机，为每个任务生成外部到达、Agent 请求、工具请求、工具响应、Agent 返回、超时、重试和最终响应事件。日志必须保留：
|
||||
|
||||
- 任务 ID、消息 ID、父消息 ID、请求响应关联 ID 和发送尝试 ID；
|
||||
- 任务类型、任务阶段和消息类型；
|
||||
- 来源节点、逻辑目标节点、实际下一跳和状态转移；
|
||||
- 时间戳、状态持续时间和队列长度；
|
||||
- 消息大小、成功状态和重试次数。
|
||||
|
||||
### 1.3.4 第四步：训练与测试隔离
|
||||
|
||||
按完整任务划分训练集、验证集与测试集。训练集只用于估计参数；验证集用于选择持续时间和消息大小分布、调整模型参数；测试集不得用于调参，只按任务聚合得到内部字节数、端到端延迟、消息数、工具调用数、重试数和成功率，作为最终模拟实验的对照值。
|
||||
|
||||
### 1.3.5 第五步：快速实验
|
||||
|
||||
| 实验 | 自变量 | 主要输出 |
|
||||
|---|---|---|
|
||||
| 预测验证 | 任务类型 | 流量、延迟、消息数预测误差 |
|
||||
| 基线对比 | 模型版本 | MAE、RMSE、MAPE |
|
||||
| 压力实验 | 外部任务到达率 | 吞吐量、P95延迟、峰值队列、丢弃率 |
|
||||
| 重试实验 | 超时概率、重试上限 | 成功率、平均重试数、流量放大系数 |
|
||||
|
||||
### 1.3.6 第六步：结果输出与使用边界
|
||||
|
||||
程序自动输出原始事件 CSV、行为画像 JSON、估计参数 JSON、实验结果 CSV 和图表。模拟实验主要用于验证模型机制、筛选关键参数和形成比赛报告的初步图表，所有结果必须标注“模拟数据”。获得真实运行日志后，保持相同实验管线，用真实数据重新估参和复验。
|
||||
|
||||
# 2 实验环境与复现规范
|
||||
|
||||
## 2.1 待记录环境
|
||||
|
||||
| 项目 | 记录内容 |
|
||||
|---|---|
|
||||
| 硬件 | CPU型号、核数、内存、操作系统 |
|
||||
| 软件 | Python及依赖版本、仿真器提交版本 |
|
||||
| 配置 | 拓扑文件、参数文件、任务场景文件 |
|
||||
| 随机性 | 主随机种子、重复实验种子列表 |
|
||||
| 运行 | 开始时间、结束时间、预热期、仿真时长 |
|
||||
| 输出 | 原始事件日志、聚合指标、图表脚本 |
|
||||
|
||||
## 2.2 目录建议
|
||||
|
||||
```text
|
||||
experiments/
|
||||
configs/ # 场景、拓扑和参数
|
||||
raw_logs/ # 原始Agent或仿真事件日志
|
||||
processed/ # 清洗后的标准数据
|
||||
scripts/ # 运行、统计和绘图脚本
|
||||
results/ # 每次实验的机器可读结果
|
||||
figures/ # 报告图表
|
||||
manifests/ # 环境、版本、种子与校验信息
|
||||
```
|
||||
|
||||
## 2.3 数据划分
|
||||
|
||||
如有真实任务日志，建议按任务而非单条消息划分，避免同一任务的消息同时出现在训练集和测试集。
|
||||
|
||||
- 训练集：60%，用于参数估计；
|
||||
- 验证集：20%，用于选择分布和超参数；
|
||||
- 测试集：20%，只用于最终评估。
|
||||
|
||||
若数据具有明显时间漂移，应采用前段训练、后段测试的时间切分，并额外报告随机切分结果。
|
||||
|
||||
# 3 指标体系
|
||||
|
||||
## 3.1 预测误差
|
||||
|
||||
对节点流量、链路流量、吞吐量和平均延迟计算：
|
||||
|
||||
$$
|
||||
MAE=\frac{1}{n}\sum_{i=1}^{n}|\hat y_i-y_i|
|
||||
$$
|
||||
|
||||
$$
|
||||
RMSE=\sqrt{\frac{1}{n}\sum_{i=1}^{n}(\hat y_i-y_i)^2}
|
||||
$$
|
||||
|
||||
$$
|
||||
MAPE=\frac{100\%}{n}\sum_{i=1}^{n}
|
||||
\left|\frac{\hat y_i-y_i}{y_i+\varepsilon}\right|
|
||||
$$
|
||||
|
||||
对于真实值接近零的对象，MAPE 不稳定，应同时报告 MAE、SMAPE 或加权 MAPE。
|
||||
|
||||
## 3.2 分布与尾部指标
|
||||
|
||||
- 平均延迟、中位数、P90、P95、P99；
|
||||
- 队列长度分布及最大值；
|
||||
- 消息大小和状态持续时间分布距离；
|
||||
- 可选使用 KS 统计量或 Wasserstein 距离比较分布。
|
||||
|
||||
## 3.3 热点识别
|
||||
|
||||
将利用率或流量处于前 $k\%$ 的节点/链路定义为热点，计算 Precision、Recall、F1 和 Top-K 命中率。
|
||||
|
||||
## 3.4 仿真性能
|
||||
|
||||
- 总运行时间；
|
||||
- 峰值内存；
|
||||
- 每秒处理事件数；
|
||||
- 单任务平均事件数；
|
||||
- 节点规模增加时的时间与内存增长率。
|
||||
|
||||
## 3.5 稳定性与可靠性
|
||||
|
||||
- 任务成功率和失败率；
|
||||
- 超时率和平均重试次数；
|
||||
- 流量放大系数；
|
||||
- 队列是否在仿真后段持续增长；
|
||||
- 故障恢复时间和受影响任务比例。
|
||||
|
||||
# 4 实验E1：三节点手工算例与单元验证
|
||||
|
||||
## 4.1 目的
|
||||
|
||||
验证消息生成、状态转换、链路累计、节点收发流量、超时取消和重试计数是否正确。
|
||||
|
||||
## 4.2 场景
|
||||
|
||||
```text
|
||||
外部 → A → B → C → B → A
|
||||
```
|
||||
|
||||
消息大小依次为 2、3、1、4、2 KB。关闭随机性并固定所有处理时间。分别运行：
|
||||
|
||||
1. 正常工具调用；
|
||||
2. 不调用工具直接返回；
|
||||
3. 第一次工具调用超时、第二次成功；
|
||||
4. 超过最大重试次数并失败；
|
||||
5. B 节点无处理资源，消息进入队列。
|
||||
|
||||
## 4.3 检查项
|
||||
|
||||
- 节点 A/B/C 入站和出站消息数；
|
||||
- A-B、B-C 链路累计字节数；
|
||||
- 消息路径和跳数；
|
||||
- `destination` 与逐跳 `next_hop` 的一致性；
|
||||
- 队列入队、出队和并发资源释放；
|
||||
- 节点资源状态 $q_v$ 与各消息处理上下文状态 $q_m$ 的一致性；
|
||||
- 响应成功后对应超时事件失效；
|
||||
- 任务完成或失败后不存在悬挂请求。
|
||||
|
||||
## 4.4 通过标准
|
||||
|
||||
确定性计数应与手工结果完全一致；浮点时间误差应低于预设容差；所有守恒检查通过。
|
||||
|
||||
# 5 实验E2：参数估计与分布拟合
|
||||
|
||||
## 5.1 目的
|
||||
|
||||
检验从小规模日志估计转移概率、持续时间、消息大小和失败参数的稳定性。
|
||||
|
||||
## 5.2 步骤
|
||||
|
||||
1. 清洗并按任务还原调用链；
|
||||
2. 统计各状态的转移计数和样本量；
|
||||
3. 对持续时间和消息大小比较经验分布、对数正态、Gamma 等候选；
|
||||
4. 使用验证集选择分布；
|
||||
5. 对参数进行 Bootstrap，计算 95% 置信区间；
|
||||
6. 检查任务类型、阶段和负载分层后的样本稀疏问题；
|
||||
7. 为低样本组启用平滑或上级参数回退。
|
||||
|
||||
## 5.3 输出表
|
||||
|
||||
| 参数 | 分组条件 | 样本量 | 估计值/分布 | 95%区间 | 来源 | 置信度 |
|
||||
|---|---|---:|---|---|---|---|
|
||||
| P(Think→CallTool) | 待填写 | | | | 真实/合成 | |
|
||||
| T_Think | 待填写 | | | | 真实/合成 | |
|
||||
| S_request | 待填写 | | | | 真实/合成 | |
|
||||
| p_timeout | 待填写 | | | | 压测/日志 | |
|
||||
|
||||
## 5.4 判定原则
|
||||
|
||||
不预设必须选择某种理论分布。若参数分布拟合较差，正式仿真使用经验抽样，并在报告中说明样本覆盖范围。
|
||||
|
||||
# 6 实验E3：小规模预测准确性
|
||||
|
||||
## 6.1 目的
|
||||
|
||||
使用训练集估计参数，在未参与估参的测试任务上预测流量、延迟和调用次数。
|
||||
|
||||
## 6.2 场景建议
|
||||
|
||||
- 节点规模：3、5、10；
|
||||
- 任务类型：至少 2 类；
|
||||
- 任务阶段：简单任务与工具密集任务；
|
||||
- 负载：低、中、高三个档位；
|
||||
- 每个场景包含足够任务，并运行多次随机仿真。
|
||||
|
||||
## 6.3 比较对象
|
||||
|
||||
- 各节点消息率和字节率；
|
||||
- 各链路累计流量；
|
||||
- 平均、P95、P99 延迟；
|
||||
- 平均工具调用数、下游消息数和重试数；
|
||||
- 吞吐量、失败率和平均队列长度。
|
||||
|
||||
## 6.4 预期图表
|
||||
|
||||
1. 预测值—实测值散点图及 $y=x$ 参考线；
|
||||
2. 各节点流量误差条形图；
|
||||
3. 实测与预测延迟累积分布曲线；
|
||||
4. 不同负载下的 MAPE/MAE 对比；
|
||||
5. 任务级流量放大系数箱线图。
|
||||
|
||||
## 6.5 初步验收目标
|
||||
|
||||
在没有比赛官方阈值时，不应预先承诺固定精度。可使用以下内部目标推动迭代：完整模型在多数主要指标上优于所有基线；测试误差的置信区间稳定；高负载误差上升能够得到合理解释。最终报告填写真实数值。
|
||||
|
||||
# 7 实验E4：基线模型对比
|
||||
|
||||
## 7.1 基线定义
|
||||
|
||||
| 编号 | 基线 | 描述 |
|
||||
|---|---|---|
|
||||
| B0 | 静态平均倍数 | 外部流量乘以固定放大系数 |
|
||||
| B1 | 纯拓扑随机游走 | 仅按连接和固定路由概率传播 |
|
||||
| B2 | 简单排队模型 | 到达率和服务率驱动，不表达任务状态 |
|
||||
| B3 | 单层状态机 | 节点行为和跨节点传播不分层 |
|
||||
| M | 完整模型 | 双层状态机、分层参数、队列和重试闭环 |
|
||||
|
||||
## 7.2 公平性要求
|
||||
|
||||
- 各模型使用相同训练任务和测试任务；
|
||||
- 可共享的外部到达率、平均消息大小和节点总处理能力 $\mu$ 保持一致；
|
||||
- 不允许完整模型使用测试集参数；
|
||||
- 同时比较精度和运行开销，避免只比较预测误差。
|
||||
|
||||
## 7.3 结果表模板
|
||||
|
||||
| 模型 | 节点流量MAPE | 链路流量MAPE | 平均延迟误差 | P95误差 | 运行时间 |
|
||||
|---|---:|---:|---:|---:|---:|
|
||||
| B0 | | | | | |
|
||||
| B1 | | | | | |
|
||||
| B2 | | | | | |
|
||||
| B3 | | | | | |
|
||||
| M | | | | | |
|
||||
|
||||
# 8 实验E5：消融实验
|
||||
|
||||
## 8.1 消融项
|
||||
|
||||
| 消融版本 | 移除内容 | 要验证的假设 |
|
||||
|---|---|---|
|
||||
| A1 | 移除任务阶段修正 | 阶段信息能提升行为预测 |
|
||||
| A2 | 移除局部拓扑和邻居负载 | 拓扑负载影响目标选择与热点 |
|
||||
| A3 | 使用固定平均处理时间 | 长尾分布影响尾延迟 |
|
||||
| A4 | 移除节点队列 | 队列是高负载延迟的关键来源 |
|
||||
| A5 | 移除失败与重试 | 重试影响流量放大与稳定性 |
|
||||
| A6 | 固定节点类型替代能力向量 | 能力表示改善异构节点泛化 |
|
||||
|
||||
## 8.2 分析方式
|
||||
|
||||
比较完整模型与各消融版本在低、中、高负载下的误差变化。若某模块对所有场景几乎没有贡献，应检查参数是否未被正确使用，或重新评估模块复杂度是否值得保留。
|
||||
|
||||
# 9 实验E6：压力与容量拐点
|
||||
|
||||
## 9.1 自变量
|
||||
|
||||
逐步提高外部到达率：
|
||||
|
||||
$$
|
||||
\lambda\in\{0.2,0.4,0.6,0.8,1.0,1.2,1.5\}\times C_{baseline}
|
||||
$$
|
||||
|
||||
其中 $C_{baseline}$ 是基准系统的估计处理能力。每个负载档运行足够长的预热期和统计期。
|
||||
|
||||
## 9.2 观测指标
|
||||
|
||||
- 吞吐量；
|
||||
- 平均、P95、P99 延迟；
|
||||
- 关键节点队列长度；
|
||||
- 超时率、失败率和重试率；
|
||||
- 节点与链路利用率；
|
||||
- 流量放大系数。
|
||||
|
||||
## 9.3 容量拐点定义
|
||||
|
||||
可结合以下现象定义容量拐点：吞吐量不再随到达率线性增长；队列在统计期持续增长；P95 延迟突增；失败率超过业务阈值；重试导致内部流量明显非线性增加。
|
||||
|
||||
## 9.4 预期图表
|
||||
|
||||
- 到达率—吞吐量曲线；
|
||||
- 到达率—P95/P99 延迟曲线；
|
||||
- 时间—队列长度曲线；
|
||||
- 到达率—超时率/重试率曲线；
|
||||
- 到达率—流量放大系数曲线。
|
||||
|
||||
# 10 实验E7：故障与重试放大
|
||||
|
||||
## 10.1 场景矩阵
|
||||
|
||||
| 因素 | 建议水平 |
|
||||
|---|---|
|
||||
| 节点故障比例 | 0%、1%、5%、10% |
|
||||
| 链路带宽下降 | 0%、25%、50%、75% |
|
||||
| 基础超时概率 | 0、0.02、0.05、0.10、0.20 |
|
||||
| 最大重试次数 | 0、1、2、3、5 |
|
||||
| 退避策略 | 无退避、固定退避、指数退避 |
|
||||
| 目标选择 | 固定节点、负载感知、故障感知 |
|
||||
|
||||
## 10.2 关键问题
|
||||
|
||||
1. 哪种重试上限在成功率和额外流量之间更均衡？
|
||||
2. 指数退避能否减轻拥塞雪崩？
|
||||
3. 负载感知或故障感知路由能否缩小影响范围？
|
||||
4. 哪些热点节点故障会造成最大任务失败率？
|
||||
|
||||
## 10.3 结果展示
|
||||
|
||||
使用热力图展示“超时概率 × 重试上限”对成功率和流量放大系数的影响；使用拓扑图展示故障前后的热点迁移；使用时间曲线展示拥塞与恢复过程。
|
||||
|
||||
# 11 实验E8：拓扑和调度策略对比
|
||||
|
||||
## 11.1 拓扑
|
||||
|
||||
- 星型：中心协调节点连接所有执行节点；
|
||||
- 树型：分层协调和任务拆分；
|
||||
- 随机稀疏图：一般协作网络；
|
||||
- 小世界：高聚类、少量远程连接；
|
||||
- 无标度图：少量枢纽节点拥有高连接度。
|
||||
|
||||
## 11.2 策略
|
||||
|
||||
- 最短跳数；
|
||||
- 随机可行邻居；
|
||||
- 最短队列；
|
||||
- 能力匹配优先；
|
||||
- 综合能力、距离、负载和可靠性的加权策略。
|
||||
|
||||
## 11.3 指标
|
||||
|
||||
比较平均跳数、流量集中度、最大节点利用率、任务延迟、成功率和重路由次数。重点讨论不同拓扑是否会形成单点瓶颈，以及负载感知策略是否以额外跳数换取更低尾延迟。
|
||||
|
||||
# 12 实验E9：规模扩展与计算性能
|
||||
|
||||
## 12.1 规模设置
|
||||
|
||||
```text
|
||||
10、100、1 000、10 000、100 000 个仿真节点
|
||||
```
|
||||
|
||||
对每个规模控制平均度数、任务到达率与节点数量的比例，并分别报告低负载和中负载结果。若 100000 节点无法在现有硬件完成，应如实报告达到的最大规模、瓶颈和优化方向。
|
||||
|
||||
## 12.2 测量
|
||||
|
||||
- 初始化时间；
|
||||
- 仿真运行时间；
|
||||
- 峰值内存；
|
||||
- 每秒事件数；
|
||||
- 事件总数；
|
||||
- 结果聚合时间；
|
||||
- 不同规模下的预测指标稳定性。
|
||||
|
||||
## 12.3 对比版本
|
||||
|
||||
如实现条件允许，对比：
|
||||
|
||||
1. 固定时间步与离散事件；
|
||||
2. 全量节点与同构节点聚合；
|
||||
3. 不同优先队列实现；
|
||||
4. 单线程与分区并行版本。
|
||||
|
||||
# 13 实验E10：敏感性与不确定性分析
|
||||
|
||||
## 13.1 关键参数
|
||||
|
||||
- 工具调用概率；
|
||||
- 下游任务数量；
|
||||
- 消息大小均值与方差；
|
||||
- 节点处理速度；
|
||||
- 链路带宽和时延；
|
||||
- 超时概率与重试上限；
|
||||
- 外部任务突发程度。
|
||||
|
||||
## 13.2 方法
|
||||
|
||||
第一阶段使用单因素局部敏感性分析；第二阶段可使用拉丁超立方抽样或 Sobol 方法分析全局敏感性。对高不确定参数从其估计区间中抽样，输出预测指标的置信区间，而不是只给单点预测。
|
||||
|
||||
## 13.3 输出
|
||||
|
||||
- 参数敏感性排序；
|
||||
- 龙卷风图；
|
||||
- 参数变化与输出变化曲线；
|
||||
- 预测区间随样本量的变化；
|
||||
- 最需要补采数据的参数列表。
|
||||
|
||||
# 14 数据质量与守恒检查
|
||||
|
||||
每次实验自动执行以下检查：
|
||||
|
||||
- 每条消息有且仅有一个 task_id 和 message_id；
|
||||
- 除外部输入、最终输出和丢弃外，发送消息数与接收/在途消息数守恒；
|
||||
- 节点并发数不超过上限，队列长度不为负；
|
||||
- 链路累计字节数等于经过该链路消息大小之和；
|
||||
- 已完成请求不会再次触发有效超时；
|
||||
- 任务完成后未完成子请求数为零或被明确标记为取消；
|
||||
- 聚合指标能够由原始事件日志重新计算。
|
||||
|
||||
# 15 报告图表清单
|
||||
|
||||
最终《验证与评估报告》至少包含：
|
||||
|
||||
1. 实验环境与数据集统计表；
|
||||
2. 参数估计及置信区间表；
|
||||
3. 三节点手工对账表；
|
||||
4. 完整模型与基线的误差对比表；
|
||||
5. 预测值—实测值散点图；
|
||||
6. 延迟 CDF 或分位数对比图；
|
||||
7. 消融实验条形图；
|
||||
8. 到达率—吞吐量—尾延迟曲线；
|
||||
9. 超时率—重试次数—流量放大热力图；
|
||||
10. 拓扑热点图；
|
||||
11. 节点规模—运行时间/内存曲线；
|
||||
12. 敏感性排序图；
|
||||
13. 失败案例及误差来源表。
|
||||
|
||||
# 16 执行排期
|
||||
|
||||
| 周期 | 任务 | 完成判据 |
|
||||
|---|---|---|
|
||||
| 第1阶段 | 仿真器最小闭环与E1 | 手工算例全部通过 |
|
||||
| 第2阶段 | 日志模式、合成数据与E2 | 参数表可自动生成 |
|
||||
| 第3阶段 | E3基准预测与E4基线 | 获得第一版误差结果 |
|
||||
| 第4阶段 | E5消融与E6压力 | 明确模块贡献和容量拐点 |
|
||||
| 第5阶段 | E7故障、E8拓扑 | 得到重试与路由结论 |
|
||||
| 第6阶段 | E9规模、E10敏感性 | 完成性能和不确定性分析 |
|
||||
| 第7阶段 | 报告整合与复现检查 | 图表可一键复现、结论有数据支撑 |
|
||||
|
||||
# 17 最终报告写作模板
|
||||
|
||||
正式报告建议按以下顺序组织：
|
||||
|
||||
1. 验证目标与实验环境；
|
||||
2. 数据来源、清洗和参数估计；
|
||||
3. 实现正确性验证；
|
||||
4. 预测准确性与基线对比；
|
||||
5. 消融实验；
|
||||
6. 压力、故障和拓扑实验；
|
||||
7. 大规模仿真性能；
|
||||
8. 敏感性和不确定性；
|
||||
9. 失败案例、模型边界与改进；
|
||||
10. 结论。
|
||||
|
||||
每项结论采用“实验条件—观察数据—结论—适用范围”的格式。例如，不应只写“指数退避更好”，而应写明在哪些负载、超时率和重试次数下改善了哪些指标，以及是否牺牲了任务完成时间。
|
||||
|
||||
# 结论
|
||||
|
||||
本实验计划通过实现正确性、参数可信度、预测精度、基线对比、消融、压力、故障、拓扑、规模和敏感性十类实验，形成从代码到结论的完整证据链。执行过程中应优先完成三节点对账和小规模预测，再逐步扩展到高负载及大规模场景；所有结果必须保留参数来源、随机种子和复现配置，确保最终参赛报告可信、透明且可重复。
|
||||
@@ -0,0 +1,27 @@
|
||||
param(
|
||||
[Parameter(Mandatory=$true)][string]$InputDirectory,
|
||||
[Parameter(Mandatory=$true)][string]$PdfDirectory
|
||||
)
|
||||
$ErrorActionPreference = 'Stop'
|
||||
New-Item -ItemType Directory -Force -Path $PdfDirectory | Out-Null
|
||||
$word = New-Object -ComObject Word.Application
|
||||
$word.Visible = $false
|
||||
$word.DisplayAlerts = 0
|
||||
try {
|
||||
foreach ($file in Get-ChildItem -LiteralPath $InputDirectory -Filter '*.docx') {
|
||||
$doc = $word.Documents.Open($file.FullName, $false, $true)
|
||||
try {
|
||||
$doc.Repaginate()
|
||||
$pdf = Join-Path $PdfDirectory ($file.BaseName + '.pdf')
|
||||
$doc.ExportAsFixedFormat($pdf, 17)
|
||||
} finally {
|
||||
$doc.Close($false)
|
||||
[System.Runtime.InteropServices.Marshal]::ReleaseComObject($doc) | Out-Null
|
||||
}
|
||||
}
|
||||
} finally {
|
||||
$word.Quit()
|
||||
[System.Runtime.InteropServices.Marshal]::ReleaseComObject($word) | Out-Null
|
||||
[GC]::Collect()
|
||||
[GC]::WaitForPendingFinalizers()
|
||||
}
|
||||
@@ -0,0 +1,158 @@
|
||||
param(
|
||||
[Parameter(Mandatory=$true)][string]$InputDirectory,
|
||||
[Parameter(Mandatory=$true)][string]$PdfDirectory
|
||||
)
|
||||
|
||||
$ErrorActionPreference = 'Stop'
|
||||
New-Item -ItemType Directory -Force -Path $PdfDirectory | Out-Null
|
||||
|
||||
$wdAlignParagraphCenter = 1
|
||||
$wdAlignParagraphRight = 2
|
||||
$wdAlignParagraphJustify = 3
|
||||
$wdLineSpaceMultiple = 5
|
||||
$wdPageBreak = 7
|
||||
$wdFormatPDF = 17
|
||||
$wdFieldPage = 33
|
||||
$wdHeaderFooterPrimary = 1
|
||||
$wdCollapseEnd = 0
|
||||
$wdColorWhite = 16777215
|
||||
$wdColorDarkBlue = 9655585
|
||||
$wdColorBlue = 11621185
|
||||
$wdColorGray = 8421504
|
||||
|
||||
$word = New-Object -ComObject Word.Application
|
||||
$word.Visible = $false
|
||||
$word.DisplayAlerts = 0
|
||||
|
||||
try {
|
||||
Get-ChildItem -LiteralPath $InputDirectory -Filter '*.docx' | ForEach-Object {
|
||||
$doc = $word.Documents.Open($_.FullName)
|
||||
try {
|
||||
$doc.PageSetup.PaperSize = 2 # Letter
|
||||
$doc.PageSetup.TopMargin = $word.InchesToPoints(0.82)
|
||||
$doc.PageSetup.BottomMargin = $word.InchesToPoints(0.78)
|
||||
$doc.PageSetup.LeftMargin = $word.InchesToPoints(0.9)
|
||||
$doc.PageSetup.RightMargin = $word.InchesToPoints(0.9)
|
||||
$doc.PageSetup.HeaderDistance = $word.InchesToPoints(0.35)
|
||||
$doc.PageSetup.FooterDistance = $word.InchesToPoints(0.35)
|
||||
|
||||
$normal = $doc.Styles.Item(-1)
|
||||
$normal.Font.Name = 'Calibri'
|
||||
$normal.Font.NameFarEast = 'Microsoft YaHei'
|
||||
$normal.Font.Size = 10.5
|
||||
$normal.Font.Color = 0
|
||||
$normal.ParagraphFormat.Alignment = $wdAlignParagraphJustify
|
||||
$normal.ParagraphFormat.SpaceBefore = 0
|
||||
$normal.ParagraphFormat.SpaceAfter = 6
|
||||
$normal.ParagraphFormat.LineSpacingRule = $wdLineSpaceMultiple
|
||||
$normal.ParagraphFormat.LineSpacing = 15.5
|
||||
|
||||
$title = $doc.Styles.Item(-63)
|
||||
$title.Font.Name = 'Calibri'
|
||||
$title.Font.NameFarEast = 'Microsoft YaHei'
|
||||
$title.Font.Size = 25
|
||||
$title.Font.Bold = $true
|
||||
$title.Font.Color = $wdColorDarkBlue
|
||||
$title.ParagraphFormat.Alignment = $wdAlignParagraphCenter
|
||||
$title.ParagraphFormat.SpaceBefore = 115
|
||||
$title.ParagraphFormat.SpaceAfter = 10
|
||||
$title.ParagraphFormat.KeepWithNext = $true
|
||||
|
||||
$subtitle = $doc.Styles.Item(-75)
|
||||
$subtitle.Font.NameFarEast = 'Microsoft YaHei'
|
||||
$subtitle.Font.Name = 'Calibri'
|
||||
$subtitle.Font.Size = 14
|
||||
$subtitle.Font.Color = $wdColorGray
|
||||
$subtitle.ParagraphFormat.Alignment = $wdAlignParagraphCenter
|
||||
$subtitle.ParagraphFormat.SpaceAfter = 30
|
||||
|
||||
$headingSettings = @(
|
||||
@{ Id=-2; Size=16; Before=16; After=8; Color=$wdColorBlue },
|
||||
@{ Id=-3; Size=13; Before=12; After=6; Color=$wdColorBlue },
|
||||
@{ Id=-4; Size=11.5; Before=9; After=4; Color=$wdColorDarkBlue }
|
||||
)
|
||||
foreach ($h in $headingSettings) {
|
||||
$style = $doc.Styles.Item($h.Id)
|
||||
$style.Font.Name = 'Calibri'
|
||||
$style.Font.NameFarEast = 'Microsoft YaHei'
|
||||
$style.Font.Size = $h.Size
|
||||
$style.Font.Bold = $true
|
||||
$style.Font.Color = $h.Color
|
||||
$style.ParagraphFormat.SpaceBefore = $h.Before
|
||||
$style.ParagraphFormat.SpaceAfter = $h.After
|
||||
$style.ParagraphFormat.KeepWithNext = $true
|
||||
$style.ParagraphFormat.KeepTogether = $true
|
||||
$style.ParagraphFormat.PageBreakBefore = $false
|
||||
}
|
||||
|
||||
foreach ($p in $doc.Paragraphs) {
|
||||
$p.Range.Font.NameFarEast = 'Microsoft YaHei'
|
||||
if ($p.Range.Text.Trim() -eq '目录') {
|
||||
$p.Alignment = $wdAlignParagraphCenter
|
||||
$p.Range.Font.Size = 18
|
||||
$p.Range.Font.Bold = $true
|
||||
$p.Range.Font.Color = $wdColorDarkBlue
|
||||
}
|
||||
}
|
||||
|
||||
foreach ($table in $doc.Tables) {
|
||||
$table.AllowAutoFit = $true
|
||||
$table.AutoFitBehavior(2)
|
||||
$table.Rows.AllowBreakAcrossPages = $true
|
||||
$table.Range.Font.Name = 'Calibri'
|
||||
$table.Range.Font.NameFarEast = 'Microsoft YaHei'
|
||||
$table.Range.Font.Size = 9
|
||||
$table.Range.ParagraphFormat.SpaceAfter = 2
|
||||
$table.Range.ParagraphFormat.LineSpacingRule = 0
|
||||
$table.Borders.Enable = 1
|
||||
if ($table.Rows.Count -gt 0) {
|
||||
$table.Rows.Item(1).Range.Font.Bold = $true
|
||||
$table.Rows.Item(1).Range.Font.Color = $wdColorWhite
|
||||
$table.Rows.Item(1).Shading.BackgroundPatternColor = $wdColorDarkBlue
|
||||
$table.Rows.Item(1).HeadingFormat = $true
|
||||
}
|
||||
$table.Range.Cells.VerticalAlignment = 1
|
||||
}
|
||||
|
||||
foreach ($section in $doc.Sections) {
|
||||
$header = $section.Headers.Item($wdHeaderFooterPrimary)
|
||||
$header.Range.Text = '大规模多智能体网络流量建模与预测'
|
||||
$header.Range.Font.NameFarEast = 'Microsoft YaHei'
|
||||
$header.Range.Font.Name = 'Calibri'
|
||||
$header.Range.Font.Size = 8.5
|
||||
$header.Range.Font.Color = $wdColorGray
|
||||
$header.Range.ParagraphFormat.Alignment = 0
|
||||
|
||||
$footer = $section.Footers.Item($wdHeaderFooterPrimary)
|
||||
$footer.Range.Text = '参赛材料初稿 | '
|
||||
$footer.Range.Font.NameFarEast = 'Microsoft YaHei'
|
||||
$footer.Range.Font.Name = 'Calibri'
|
||||
$footer.Range.Font.Size = 8.5
|
||||
$footer.Range.Font.Color = $wdColorGray
|
||||
$footer.Range.ParagraphFormat.Alignment = $wdAlignParagraphRight
|
||||
$range = $footer.Range
|
||||
$range.Collapse($wdCollapseEnd)
|
||||
[void]$footer.Range.Fields.Add($range, $wdFieldPage)
|
||||
}
|
||||
|
||||
if ($doc.TablesOfContents.Count -gt 0) {
|
||||
$doc.TablesOfContents.Item(1).Update()
|
||||
}
|
||||
$doc.Fields.Update() | Out-Null
|
||||
$doc.Repaginate()
|
||||
$doc.Save()
|
||||
$pdfPath = Join-Path $PdfDirectory ($_.BaseName + '.pdf')
|
||||
$doc.ExportAsFixedFormat($pdfPath, $wdFormatPDF)
|
||||
}
|
||||
finally {
|
||||
$doc.Close($true)
|
||||
[System.Runtime.InteropServices.Marshal]::ReleaseComObject($doc) | Out-Null
|
||||
}
|
||||
}
|
||||
}
|
||||
finally {
|
||||
$word.Quit()
|
||||
[System.Runtime.InteropServices.Marshal]::ReleaseComObject($word) | Out-Null
|
||||
[GC]::Collect()
|
||||
[GC]::WaitForPendingFinalizers()
|
||||
}
|
||||
@@ -0,0 +1,81 @@
|
||||
param([Parameter(Mandatory=$true)][string]$Directory)
|
||||
$ErrorActionPreference='Stop'
|
||||
Add-Type -AssemblyName System.IO.Compression.FileSystem
|
||||
$ns='http://schemas.openxmlformats.org/wordprocessingml/2006/main'
|
||||
|
||||
function Set-Attr($node,$name,$value,$xml){
|
||||
$attr=$xml.CreateAttribute('w',$name,$ns); $attr.Value=[string]$value
|
||||
[void]$node.Attributes.SetNamedItem($attr)
|
||||
}
|
||||
function Ensure-Child($parent,$local,$xml){
|
||||
$child=$parent.SelectSingleNode("w:$local",$script:nsmgr)
|
||||
if(-not $child){$child=$xml.CreateElement('w',$local,$ns); [void]$parent.AppendChild($child)}
|
||||
return $child
|
||||
}
|
||||
function Set-Style($xml,$styleId,$font,$eastAsia,$sizeHalf,$color,$bold,$before,$after,$line){
|
||||
$s=$xml.SelectSingleNode("//w:style[@w:styleId='$styleId']",$script:nsmgr); if(-not $s){return}
|
||||
$rPr=Ensure-Child $s 'rPr' $xml
|
||||
$fonts=Ensure-Child $rPr 'rFonts' $xml; Set-Attr $fonts 'ascii' $font $xml; Set-Attr $fonts 'hAnsi' $font $xml; Set-Attr $fonts 'eastAsia' $eastAsia $xml
|
||||
$sz=Ensure-Child $rPr 'sz' $xml; Set-Attr $sz 'val' $sizeHalf $xml
|
||||
$szCs=Ensure-Child $rPr 'szCs' $xml; Set-Attr $szCs 'val' $sizeHalf $xml
|
||||
$c=Ensure-Child $rPr 'color' $xml; Set-Attr $c 'val' $color $xml
|
||||
$b=$rPr.SelectSingleNode('w:b',$script:nsmgr)
|
||||
if($bold -and -not $b){$b=$xml.CreateElement('w','b',$ns); [void]$rPr.AppendChild($b)} elseif(-not $bold -and $b){[void]$rPr.RemoveChild($b)}
|
||||
$pPr=Ensure-Child $s 'pPr' $xml
|
||||
$spacing=Ensure-Child $pPr 'spacing' $xml; Set-Attr $spacing 'before' $before $xml; Set-Attr $spacing 'after' $after $xml; Set-Attr $spacing 'line' $line $xml; Set-Attr $spacing 'lineRule' 'auto' $xml
|
||||
}
|
||||
|
||||
foreach($file in Get-ChildItem -LiteralPath $Directory -Filter '*.docx'){
|
||||
$tmp=Join-Path $Directory ('.tmp_'+[guid]::NewGuid().ToString('N'))
|
||||
[IO.Compression.ZipFile]::ExtractToDirectory($file.FullName,$tmp)
|
||||
try{
|
||||
[xml]$styles=Get-Content -Raw -Encoding UTF8 (Join-Path $tmp 'word\styles.xml')
|
||||
$script:nsmgr=New-Object Xml.XmlNamespaceManager($styles.NameTable); $nsmgr.AddNamespace('w',$ns)
|
||||
Set-Style $styles 'Normal' 'Calibri' 'Microsoft YaHei' 21 '000000' $false 0 120 300
|
||||
Set-Style $styles 'Title' 'Calibri' 'Microsoft YaHei' 50 '17365D' $true 1200 240 240
|
||||
Set-Style $styles 'Subtitle' 'Calibri' 'Microsoft YaHei' 28 '666666' $false 0 360 280
|
||||
Set-Style $styles 'Heading1' 'Calibri' 'Microsoft YaHei' 32 '2E74B5' $true 320 160 280
|
||||
Set-Style $styles 'Heading2' 'Calibri' 'Microsoft YaHei' 26 '2E74B5' $true 240 120 280
|
||||
Set-Style $styles 'Heading3' 'Calibri' 'Microsoft YaHei' 23 '1F4D78' $true 180 80 280
|
||||
$styles.Save((Join-Path $tmp 'word\styles.xml'))
|
||||
|
||||
[xml]$doc=Get-Content -Raw -Encoding UTF8 (Join-Path $tmp 'word\document.xml')
|
||||
$script:nsmgr=New-Object Xml.XmlNamespaceManager($doc.NameTable); $nsmgr.AddNamespace('w',$ns)
|
||||
foreach($sect in $doc.SelectNodes('//w:sectPr',$nsmgr)){
|
||||
$pgSz=Ensure-Child $sect 'pgSz' $doc; Set-Attr $pgSz 'w' 12240 $doc; Set-Attr $pgSz 'h' 15840 $doc
|
||||
$pgMar=Ensure-Child $sect 'pgMar' $doc; Set-Attr $pgMar 'top' 1224 $doc; Set-Attr $pgMar 'right' 1296 $doc; Set-Attr $pgMar 'bottom' 1152 $doc; Set-Attr $pgMar 'left' 1296 $doc; Set-Attr $pgMar 'header' 504 $doc; Set-Attr $pgMar 'footer' 504 $doc; Set-Attr $pgMar 'gutter' 0 $doc
|
||||
}
|
||||
foreach($tbl in $doc.SelectNodes('//w:tbl',$nsmgr)){
|
||||
$tblPr=Ensure-Child $tbl 'tblPr' $doc
|
||||
$style=Ensure-Child $tblPr 'tblStyle' $doc; Set-Attr $style 'val' 'TableGrid' $doc
|
||||
$layout=Ensure-Child $tblPr 'tblLayout' $doc; Set-Attr $layout 'type' 'autofit' $doc
|
||||
$first=$tbl.SelectSingleNode('w:tr[1]',$nsmgr)
|
||||
if($first){
|
||||
$trPr=Ensure-Child $first 'trPr' $doc; $hdr=Ensure-Child $trPr 'tblHeader' $doc; Set-Attr $hdr 'val' 1 $doc
|
||||
foreach($cell in $first.SelectNodes('w:tc',$nsmgr)){
|
||||
$tcPr=Ensure-Child $cell 'tcPr' $doc; $shd=Ensure-Child $tcPr 'shd' $doc; Set-Attr $shd 'fill' '17365D' $doc
|
||||
foreach($rPr in $cell.SelectNodes('.//w:rPr',$nsmgr)){ $c=Ensure-Child $rPr 'color' $doc; Set-Attr $c 'val' 'FFFFFF' $doc; if(-not $rPr.SelectSingleNode('w:b',$nsmgr)){[void]$rPr.AppendChild($doc.CreateElement('w','b',$ns))} }
|
||||
}
|
||||
}
|
||||
}
|
||||
$doc.Save((Join-Path $tmp 'word\document.xml'))
|
||||
|
||||
foreach($hf in Get-ChildItem -LiteralPath (Join-Path $tmp 'word') -Filter 'header*.xml' -ErrorAction SilentlyContinue){
|
||||
[xml]$hx=Get-Content -Raw -Encoding UTF8 $hf.FullName
|
||||
$script:nsmgr=New-Object Xml.XmlNamespaceManager($hx.NameTable); $nsmgr.AddNamespace('w',$ns)
|
||||
foreach($t in $hx.SelectNodes('//w:t',$nsmgr)){$t.InnerText='大规模多智能体网络流量建模与预测'}
|
||||
foreach($rPr in $hx.SelectNodes('//w:rPr',$nsmgr)){
|
||||
$fonts=Ensure-Child $rPr 'rFonts' $hx; Set-Attr $fonts 'eastAsia' 'Microsoft YaHei' $hx
|
||||
$sz=Ensure-Child $rPr 'sz' $hx; Set-Attr $sz 'val' 17 $hx
|
||||
$c=Ensure-Child $rPr 'color' $hx; Set-Attr $c 'val' '777777' $hx
|
||||
}
|
||||
$hx.Save($hf.FullName)
|
||||
}
|
||||
|
||||
$new=$file.FullName+'.new'
|
||||
if(Test-Path $new){Remove-Item -LiteralPath $new}
|
||||
[IO.Compression.ZipFile]::CreateFromDirectory($tmp,$new)
|
||||
Copy-Item -Force -LiteralPath $new -Destination $file.FullName
|
||||
Remove-Item -LiteralPath $new
|
||||
} finally { Remove-Item -Recurse -Force -LiteralPath $tmp }
|
||||
}
|
||||
Reference in New Issue
Block a user