新增实验代码等

This commit is contained in:
2026-08-13 16:17:59 +08:00
parent 718e371eb5
commit 2897b32d0d
56 changed files with 19641 additions and 0 deletions
@@ -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
1 task_id task_type task_phase latency_ms internal_bytes input_bytes amplification message_count tool_calls retries success
2 collaborative_analysis_00000 collaborative_analysis multi_agent_synthesis 6111.839000000004 62448 1205 51.824066390041494 7 1 0 True
3 collaborative_analysis_00001 collaborative_analysis multi_agent_synthesis 7858.875999999981 57236 2452 23.34257748776509 7 0 0 True
4 collaborative_analysis_00002 collaborative_analysis multi_agent_synthesis 3745.010999999977 36184 6916 5.231925968768074 5 1 0 True
5 collaborative_analysis_00003 collaborative_analysis multi_agent_synthesis 3370.6700000000183 15600 1146 13.612565445026178 3 0 0 True
6 collaborative_analysis_00004 collaborative_analysis multi_agent_synthesis 3970.753000000002 26927 5695 4.728182616330114 5 1 0 True
7 collaborative_analysis_00005 collaborative_analysis multi_agent_synthesis 3692.181000000005 9783 2845 3.438664323374341 3 0 0 True
8 collaborative_analysis_00006 collaborative_analysis multi_agent_synthesis 12027.614 101344 5088 19.91823899371069 9 1 0 True
9 collaborative_analysis_00007 collaborative_analysis multi_agent_synthesis 3174.7689999999975 13427 10177 1.3193475483934363 3 0 0 True
10 collaborative_analysis_00008 collaborative_analysis multi_agent_synthesis 4553.435000000008 106516 5924 17.98041863605672 13 2 0 True
11 collaborative_analysis_00009 collaborative_analysis multi_agent_synthesis 20393.187000000013 136393 8870 15.376888387824126 19 3 0 True
12 collaborative_analysis_00010 collaborative_analysis multi_agent_synthesis 9716.779000000002 43830 1420 30.866197183098592 9 2 0 True
13 collaborative_analysis_00011 collaborative_analysis multi_agent_synthesis 13658.126999999979 113877 6803 16.73923269145965 13 2 0 True
14 collaborative_analysis_00012 collaborative_analysis multi_agent_synthesis 5092.640999999986 138420 4391 31.523570940560237 13 2 0 True
15 collaborative_analysis_00013 collaborative_analysis multi_agent_synthesis 2393.601999999987 13198 8494 1.5538026842477042 3 0 0 True
16 collaborative_analysis_00014 collaborative_analysis multi_agent_synthesis 7330.83400000001 65750 876 75.05707762557077 11 2 0 True
17 collaborative_analysis_00015 collaborative_analysis multi_agent_synthesis 16492.502 180400 2157 83.63467779323133 23 3 0 True
18 collaborative_analysis_00016 collaborative_analysis multi_agent_synthesis 16875.831000000006 205302 2605 78.81074856046065 19 3 0 True
19 collaborative_analysis_00017 collaborative_analysis multi_agent_synthesis 9850.209000000006 147782 1988 74.33702213279678 19 3 0 True
20 collaborative_analysis_00018 collaborative_analysis multi_agent_synthesis 10007.738999999987 126126 4218 29.90184921763869 15 2 0 True
21 collaborative_analysis_00019 collaborative_analysis multi_agent_synthesis 11525.198999999986 106483 1192 89.33137583892618 7 1 0 True
22 collaborative_analysis_00020 collaborative_analysis multi_agent_synthesis 5159.906000000006 59557 2210 26.94886877828054 9 2 0 True
23 collaborative_analysis_00021 collaborative_analysis multi_agent_synthesis 4791.642999999994 57467 18445 3.1155868799132556 5 0 0 True
24 collaborative_analysis_00022 collaborative_analysis multi_agent_synthesis 11351.583000000006 75128 3315 22.663046757164405 9 1 0 True
25 collaborative_analysis_00023 collaborative_analysis multi_agent_synthesis 8277.253999999999 39603 5217 7.591144335825187 5 1 0 True
26 collaborative_analysis_00024 collaborative_analysis multi_agent_synthesis 19919.341000000004 167247 1166 143.43653516295026 23 5 0 True
27 collaborative_analysis_00025 collaborative_analysis multi_agent_synthesis 9099.73500000001 69536 6843 10.161625018266841 11 1 0 True
28 collaborative_analysis_00026 collaborative_analysis multi_agent_synthesis 3098.5450000000014 55189 7507 7.351671773011856 11 2 0 True
29 collaborative_analysis_00027 collaborative_analysis multi_agent_synthesis 6933.150000000012 128239 5952 21.545530913978496 13 3 0 True
30 collaborative_analysis_00028 collaborative_analysis multi_agent_synthesis 14684.41899999999 164414 1446 113.70262793914246 18 5 1 True
31 collaborative_analysis_00029 collaborative_analysis multi_agent_synthesis 22606.593000000004 130445 2700 48.31296296296296 13 3 2 True
32 collaborative_analysis_00030 collaborative_analysis multi_agent_synthesis 7566.215999999997 53530 2840 18.848591549295776 7 0 0 True
33 collaborative_analysis_00031 collaborative_analysis multi_agent_synthesis 9549.07 182717 560 326.28035714285716 11 2 0 True
34 collaborative_analysis_00032 collaborative_analysis multi_agent_synthesis 16413.354 140512 4336 32.40590405904059 13 1 0 True
35 collaborative_analysis_00033 collaborative_analysis multi_agent_synthesis 3107.8390000000127 25062 1526 16.42332896461337 3 0 0 True
36 collaborative_analysis_00034 collaborative_analysis multi_agent_synthesis 2382.689999999997 37813 4410 8.57437641723356 5 1 0 True
37 collaborative_analysis_00035 collaborative_analysis multi_agent_synthesis 6573.08900000001 42752 1231 34.72948822095857 9 2 0 True
38 collaborative_analysis_00036 collaborative_analysis multi_agent_synthesis 14503.11400000001 179234 7724 23.20481615743138 23 6 1 True
39 collaborative_analysis_00037 collaborative_analysis multi_agent_synthesis 6998.415999999992 40737 4407 9.243703199455412 5 1 0 True
40 collaborative_analysis_00038 collaborative_analysis multi_agent_synthesis 9218.387000000006 76646 5615 13.650222617987533 12 3 1 True
41 collaborative_analysis_00039 collaborative_analysis multi_agent_synthesis 14171.648999999974 82798 3958 20.919151086407275 13 2 0 True
42 collaborative_analysis_00040 collaborative_analysis multi_agent_synthesis 16203.926999999992 192384 4272 45.03370786516854 19 2 0 True
43 collaborative_analysis_00041 collaborative_analysis multi_agent_synthesis 8077.832999999999 86864 14703 5.907909950350269 9 1 0 True
44 collaborative_analysis_00042 collaborative_analysis multi_agent_synthesis 11980.147000000017 175669 4129 42.545168321627514 17 2 0 True
45 collaborative_analysis_00043 collaborative_analysis multi_agent_synthesis 8383.41299999999 86553 4556 18.99758560140474 11 1 0 True
46 collaborative_analysis_00044 collaborative_analysis multi_agent_synthesis 3781.3569999999854 21537 2248 9.580516014234876 5 1 0 True
47 collaborative_analysis_00045 collaborative_analysis multi_agent_synthesis 2871.480999999989 29178 3997 7.299974981235927 5 1 0 True
48 collaborative_analysis_00046 collaborative_analysis multi_agent_synthesis 1987.737999999979 21361 8073 2.6459804285891244 3 0 0 True
49 collaborative_analysis_00047 collaborative_analysis multi_agent_synthesis 10075.866999999987 219312 9941 22.061362036012472 17 3 0 True
50 collaborative_analysis_00048 collaborative_analysis multi_agent_synthesis 6179.957999999999 70354 2470 28.4834008097166 5 1 0 True
51 collaborative_analysis_00049 collaborative_analysis multi_agent_synthesis 3145.8080000000164 28609 4669 6.127436281859071 3 0 0 True
52 collaborative_analysis_00050 collaborative_analysis multi_agent_synthesis 6249.4649999999865 28317 882 32.105442176870746 7 1 0 True
53 collaborative_analysis_00051 collaborative_analysis multi_agent_synthesis 11702.425000000005 187198 1275 146.82196078431372 17 2 0 True
54 collaborative_analysis_00052 collaborative_analysis multi_agent_synthesis 10426.145999999988 122179 1403 87.08410548823949 13 2 0 True
55 collaborative_analysis_00053 collaborative_analysis multi_agent_synthesis 3776.5890000000013 10701 3073 3.482264887731858 3 0 0 True
56 collaborative_analysis_00054 collaborative_analysis multi_agent_synthesis 6411.059999999992 122716 3644 33.6761800219539 13 3 0 True
57 collaborative_analysis_00055 collaborative_analysis multi_agent_synthesis 9190.782999999981 87827 8202 10.707998049256279 13 1 0 True
58 collaborative_analysis_00056 collaborative_analysis multi_agent_synthesis 26072.79299999999 196393 2732 71.88616398243046 22 5 1 True
59 collaborative_analysis_00057 collaborative_analysis multi_agent_synthesis 6656.256000000013 33081 7347 4.502654144548796 7 1 0 True
60 collaborative_analysis_00058 collaborative_analysis multi_agent_synthesis 5274.61199999999 58229 9303 6.259163710630979 8 2 1 True
61 collaborative_analysis_00059 collaborative_analysis multi_agent_synthesis 5612.335999999999 17516 7543 2.3221529895267135 3 0 0 True
62 collaborative_analysis_00060 collaborative_analysis multi_agent_synthesis 7323.184999999995 88159 6584 13.389884568651276 5 1 0 True
63 collaborative_analysis_00061 collaborative_analysis multi_agent_synthesis 13041.410999999982 39582 4651 8.510427864975274 5 0 0 True
64 collaborative_analysis_00062 collaborative_analysis multi_agent_synthesis 5737.938000000014 55676 4041 13.777777777777779 11 2 0 True
65 collaborative_analysis_00063 collaborative_analysis multi_agent_synthesis 13871.848999999998 111676 5758 19.39492879472039 18 5 1 True
66 collaborative_analysis_00064 collaborative_analysis multi_agent_synthesis 14159.884000000005 93620 743 126.00269179004037 11 2 0 True
67 collaborative_analysis_00065 collaborative_analysis multi_agent_synthesis 2143.2680000000064 44223 2414 18.319386909693456 5 0 0 True
68 collaborative_analysis_00066 collaborative_analysis multi_agent_synthesis 9103.234999999984 120161 2301 52.22120817036071 11 0 0 True
69 collaborative_analysis_00067 collaborative_analysis multi_agent_synthesis 7975.786999999997 51818 2211 23.43645409317051 9 2 0 True
70 collaborative_analysis_00068 collaborative_analysis multi_agent_synthesis 10306.556999999997 143550 1168 122.90239726027397 15 3 0 True
71 collaborative_analysis_00069 collaborative_analysis multi_agent_synthesis 10491.949999999975 88142 1034 85.24371373307544 13 3 0 True
72 collaborative_analysis_00070 collaborative_analysis multi_agent_synthesis 5671.043999999994 92836 4373 21.229361994054425 7 1 0 True
73 collaborative_analysis_00071 collaborative_analysis multi_agent_synthesis 2233.918000000017 35792 908 39.418502202643175 5 1 0 True
74 collaborative_analysis_00072 collaborative_analysis multi_agent_synthesis 2779.2799999999997 19132 1140 16.782456140350877 3 0 0 True
75 collaborative_analysis_00073 collaborative_analysis multi_agent_synthesis 5933.890999999989 53137 2409 22.057700290577003 7 1 0 True
76 collaborative_analysis_00074 collaborative_analysis multi_agent_synthesis 11494.603000000012 198018 8671 22.836812363049244 15 5 1 True
77 collaborative_analysis_00075 collaborative_analysis multi_agent_synthesis 3800.8010000000068 92249 1891 48.78318350079323 7 0 0 True
78 collaborative_analysis_00076 collaborative_analysis multi_agent_synthesis 15271.408000000009 110064 4836 22.759305210918114 13 4 2 True
79 collaborative_analysis_00077 collaborative_analysis multi_agent_synthesis 3524.1379999999936 49633 2359 21.03984739296312 7 0 0 True
80 collaborative_analysis_00078 collaborative_analysis multi_agent_synthesis 1085.5840000000114 34459 1481 23.267386900742743 3 0 0 True
81 collaborative_analysis_00079 collaborative_analysis multi_agent_synthesis 3396.9510000000014 7311 4899 1.492345376607471 3 0 0 True
82 collaborative_analysis_00080 collaborative_analysis multi_agent_synthesis 7375.2580000000025 40747 2612 15.599923430321592 10 3 1 True
83 collaborative_analysis_00081 collaborative_analysis multi_agent_synthesis 11392.599000000018 125175 5129 24.405342171963344 17 5 1 True
84 collaborative_analysis_00082 collaborative_analysis multi_agent_synthesis 4221.8009999999995 46903 1193 39.3151718357083 3 0 0 True
85 collaborative_analysis_00083 collaborative_analysis multi_agent_synthesis 4469.9559999999965 34392 7835 4.389534141671985 5 0 0 True
86 collaborative_analysis_00084 collaborative_analysis multi_agent_synthesis 14913.923000000012 148982 4218 35.32053105737316 17 5 2 False
87 collaborative_analysis_00085 collaborative_analysis multi_agent_synthesis 3174.0640000000158 26574 2863 9.281872162067762 3 0 0 True
88 collaborative_analysis_00086 collaborative_analysis multi_agent_synthesis 6104.687000000013 29578 2252 13.134103019538188 6 2 1 True
89 collaborative_analysis_00087 collaborative_analysis multi_agent_synthesis 3079.0619999999935 23392 7001 3.3412369661476933 3 0 0 True
90 collaborative_analysis_00088 collaborative_analysis multi_agent_synthesis 15710.582000000017 123812 1087 113.90248390064397 17 3 0 True
91 collaborative_analysis_00089 collaborative_analysis multi_agent_synthesis 9594.03499999999 123841 7467 16.585107807687155 15 3 0 True
92 collaborative_analysis_00090 collaborative_analysis multi_agent_synthesis 8018.177000000009 35223 2432 14.483141447368421 7 1 0 True
93 collaborative_analysis_00091 collaborative_analysis multi_agent_synthesis 8070.577999999983 85639 1800 47.577222222222225 9 1 0 True
94 collaborative_analysis_00092 collaborative_analysis multi_agent_synthesis 6954.7670000000035 30543 2606 11.720260936300845 8 2 1 True
95 collaborative_analysis_00093 collaborative_analysis multi_agent_synthesis 2334.4150000000072 9761 1259 7.75297855440826 3 0 0 True
96 collaborative_analysis_00094 collaborative_analysis multi_agent_synthesis 3988.2240000000024 53918 4052 13.306515301085884 7 0 0 True
97 collaborative_analysis_00095 collaborative_analysis multi_agent_synthesis 6538.421999999997 67526 4362 15.480513525905549 7 1 0 True
98 collaborative_analysis_00096 collaborative_analysis multi_agent_synthesis 7050.077000000016 89764 5545 16.188277727682596 9 0 0 True
99 collaborative_analysis_00097 collaborative_analysis multi_agent_synthesis 14613.135 138234 1905 72.56377952755905 18 4 1 True
100 collaborative_analysis_00098 collaborative_analysis multi_agent_synthesis 5859.162999999995 34186 15338 2.2288433954883295 6 2 1 True
101 collaborative_analysis_00099 collaborative_analysis multi_agent_synthesis 17759.783999999996 169187 11129 15.202354209722348 21 5 0 True
102 simple_qa_00000 simple_qa answering 855.1170000000001 3448 2896 1.1906077348066297 3 0 0 True
103 simple_qa_00001 simple_qa answering 1403.896 4962 1531 3.24101894186806 3 0 0 True
104 simple_qa_00002 simple_qa answering 1171.8220000000001 4350 787 5.527318932655654 3 0 0 True
105 simple_qa_00003 simple_qa answering 1504.4239999999998 2494 375 6.650666666666667 3 0 0 True
106 simple_qa_00004 simple_qa answering 1963.5280000000002 5963 591 10.089678510998308 5 1 0 True
107 simple_qa_00005 simple_qa answering 1452.445 5943 2101 2.8286530223703 3 0 0 True
108 simple_qa_00006 simple_qa answering 825.0729999999998 3757 1209 3.10752688172043 3 0 0 True
109 simple_qa_00007 simple_qa answering 926.895 3668 2132 1.7204502814258913 3 0 0 True
110 simple_qa_00008 simple_qa answering 1005.903 4694 1529 3.0699803793328972 3 0 0 True
111 simple_qa_00009 simple_qa answering 1038.875 5016 1632 3.073529411764706 3 0 0 True
112 simple_qa_00010 simple_qa answering 659.4789999999992 9518 859 11.080325960419092 3 0 0 True
113 simple_qa_00011 simple_qa answering 1125.273 3965 1038 3.8198458574181116 3 0 0 True
114 simple_qa_00012 simple_qa answering 1077.1380000000015 5386 1219 4.418375717801476 3 0 0 True
115 simple_qa_00013 simple_qa answering 1004.5659999999988 5660 889 6.366704161979753 3 0 0 True
116 simple_qa_00014 simple_qa answering 996.1830000000002 4420 1161 3.8070628768303187 3 0 0 True
117 simple_qa_00015 simple_qa answering 860.6720000000009 4252 1484 2.8652291105121295 3 0 0 True
118 simple_qa_00016 simple_qa answering 781.1749999999993 6704 1189 5.638351555929352 3 0 0 True
119 simple_qa_00017 simple_qa answering 700.6979999999992 4185 1526 2.7424639580602883 3 0 0 True
120 simple_qa_00018 simple_qa answering 1115.2699999999988 5439 1075 5.05953488372093 3 0 0 True
121 simple_qa_00019 simple_qa answering 850.3690000000006 3539 1636 2.16320293398533 3 0 0 True
122 simple_qa_00020 simple_qa answering 823.193999999999 5658 1063 5.322671683913453 3 0 0 True
123 simple_qa_00021 simple_qa answering 930.963000000002 6726 2009 3.3479342956694875 3 0 0 True
124 simple_qa_00022 simple_qa answering 742.083000000001 5048 1822 2.770581778265642 3 0 0 True
125 simple_qa_00023 simple_qa answering 1172.7469999999976 3674 1567 2.3446075303126994 3 0 0 True
126 simple_qa_00024 simple_qa answering 604.9790000000002 7257 1006 7.213717693836978 3 0 0 True
127 simple_qa_00025 simple_qa answering 1219.6170000000031 4464 2084 2.1420345489443378 3 0 0 True
128 simple_qa_00026 simple_qa answering 753.5990000000013 4068 1755 2.317948717948718 3 0 0 True
129 simple_qa_00027 simple_qa answering 791.2379999999998 5056 1373 3.6824471959213403 3 0 0 True
130 simple_qa_00028 simple_qa answering 827.5049999999986 3795 801 4.737827715355805 3 0 0 True
131 simple_qa_00029 simple_qa answering 677.6099999999979 4655 2300 2.023913043478261 3 0 0 True
132 simple_qa_00030 simple_qa answering 791.8140000000022 4267 720 5.926388888888889 3 0 0 True
133 simple_qa_00031 simple_qa answering 1215.0280000000002 7292 3124 2.3341869398207424 5 1 0 True
134 simple_qa_00032 simple_qa answering 1804.2910000000027 4607 2837 1.6238984843144166 3 0 0 True
135 simple_qa_00033 simple_qa answering 844.0370000000001 3221 1756 1.8342824601366743 3 0 0 True
136 simple_qa_00034 simple_qa answering 1057.2420000000022 5454 1504 3.6263297872340425 3 0 0 True
137 simple_qa_00035 simple_qa answering 1576.5220000000006 5750 1500 3.8333333333333335 3 0 0 True
138 simple_qa_00036 simple_qa answering 1026.4500000000005 7409 4583 1.616626663757364 3 0 0 True
139 simple_qa_00037 simple_qa answering 716.7670000000008 5122 1777 2.8823860438942037 3 0 0 True
140 simple_qa_00038 simple_qa answering 982.6349999999984 7826 1145 6.834934497816594 3 0 0 True
141 simple_qa_00039 simple_qa answering 701.6949999999973 5078 670 7.57910447761194 3 0 0 True
142 simple_qa_00040 simple_qa answering 1318.7110000000005 5824 2164 2.6913123844731976 3 0 0 True
143 simple_qa_00041 simple_qa answering 839.9459999999976 6330 1513 4.183740912095175 3 0 0 True
144 simple_qa_00042 simple_qa answering 1454.4789999999991 5313 1358 3.9123711340206184 3 0 0 True
145 simple_qa_00043 simple_qa answering 1366.8249999999987 5530 733 7.544338335607094 3 0 0 True
146 simple_qa_00044 simple_qa answering 1134.8300000000008 5574 919 6.065288356909685 3 0 0 True
147 simple_qa_00045 simple_qa answering 1290.6880000000028 8607 1321 6.51551854655564 5 1 0 True
148 simple_qa_00046 simple_qa answering 887.5910000000005 5342 1220 4.378688524590164 3 0 0 True
149 simple_qa_00047 simple_qa answering 1500.1400000000017 11544 1496 7.716577540106952 5 0 0 True
150 simple_qa_00048 simple_qa answering 590.2030000000025 3429 1270 2.7 3 0 0 True
151 simple_qa_00049 simple_qa answering 1328.8580000000038 3926 1557 2.5215157353885678 3 0 0 True
152 simple_qa_00050 simple_qa answering 895.7130000000006 4332 1319 3.284306292645944 3 0 0 True
153 simple_qa_00051 simple_qa answering 754.6930000000032 6203 1342 4.62220566318927 3 0 0 True
154 simple_qa_00052 simple_qa answering 1541.4049999999975 5071 1117 4.539838854073411 3 0 0 True
155 simple_qa_00053 simple_qa answering 1177.0819999999985 8016 1230 6.517073170731707 5 1 0 True
156 simple_qa_00054 simple_qa answering 498.7519999999961 5493 391 14.048593350383632 3 0 0 True
157 simple_qa_00055 simple_qa answering 1162.9900000000007 7303 1651 4.423379769836463 3 0 0 True
158 simple_qa_00056 simple_qa answering 674.510000000005 2802 669 4.188340807174888 3 0 0 True
159 simple_qa_00057 simple_qa answering 2256.7659999999987 4338 969 4.476780185758514 3 0 0 True
160 simple_qa_00058 simple_qa answering 1575.8580000000038 10725 3214 3.336963285625389 5 1 0 True
161 simple_qa_00059 simple_qa answering 1815.6789999999958 5774 1265 4.564426877470356 3 0 0 True
162 simple_qa_00060 simple_qa answering 686.0010000000045 5624 923 6.0931744312026 3 0 0 True
163 simple_qa_00061 simple_qa answering 1254.2200000000037 6000 887 6.764374295377678 3 0 0 True
164 simple_qa_00062 simple_qa answering 945.3009999999936 7475 564 13.25354609929078 3 0 0 True
165 simple_qa_00063 simple_qa answering 841.0459999999987 3683 751 4.9041278295605855 3 0 0 True
166 simple_qa_00064 simple_qa answering 1241.6660000000022 9729 904 10.76216814159292 5 1 0 True
167 simple_qa_00065 simple_qa answering 1516.855999999997 6629 1109 5.977457168620378 5 1 0 True
168 simple_qa_00066 simple_qa answering 1183.698999999997 3552 1627 2.183159188690842 3 0 0 True
169 simple_qa_00067 simple_qa answering 995.9650000000054 8377 2106 3.977682811016144 3 0 0 True
170 simple_qa_00068 simple_qa answering 959.3050000000005 4731 1465 3.2293515358361775 3 0 0 True
171 simple_qa_00069 simple_qa answering 1188.1830000000023 3612 1113 3.2452830188679247 3 0 0 True
172 simple_qa_00070 simple_qa answering 1491.27 4065 761 5.341655716162943 3 0 0 True
173 simple_qa_00071 simple_qa answering 846.0699999999974 2898 1350 2.1466666666666665 3 0 0 True
174 simple_qa_00072 simple_qa answering 1207.8729999999994 3417 747 4.57429718875502 3 0 0 True
175 simple_qa_00073 simple_qa answering 1940.8279999999963 7028 3264 2.153186274509804 5 1 0 True
176 simple_qa_00074 simple_qa answering 1482.2769999999964 5076 1081 4.695652173913044 3 0 0 True
177 simple_qa_00075 simple_qa answering 864.4090000000019 6816 897 7.59866220735786 3 0 0 True
178 simple_qa_00076 simple_qa answering 1091.8100000000024 4841 1310 3.6954198473282442 3 0 0 True
179 simple_qa_00077 simple_qa answering 1149.9900000000025 4287 737 5.8168249660786975 3 0 0 True
180 simple_qa_00078 simple_qa answering 1253.6500000000003 6102 1037 5.884281581485053 3 0 0 True
181 simple_qa_00079 simple_qa answering 2618.4089999999997 6982 680 10.26764705882353 5 1 0 True
182 simple_qa_00080 simple_qa answering 838.6209999999962 5148 824 6.247572815533981 3 0 0 True
183 simple_qa_00081 simple_qa answering 706.4880000000003 8520 643 13.250388802488336 3 0 0 True
184 simple_qa_00082 simple_qa answering 1185.3399999999965 4372 474 9.223628691983123 3 0 0 True
185 simple_qa_00083 simple_qa answering 1010.4350000000011 8796 1347 6.5300668151447665 3 0 0 True
186 simple_qa_00084 simple_qa answering 652.358999999997 3394 1270 2.6724409448818895 3 0 0 True
187 simple_qa_00085 simple_qa answering 1272.1099999999979 5066 1257 4.030230708035004 3 0 0 True
188 simple_qa_00086 simple_qa answering 1247.2220000000007 7260 610 11.901639344262295 5 1 0 True
189 simple_qa_00087 simple_qa answering 813.3010000000027 3990 2088 1.910919540229885 3 0 0 True
190 simple_qa_00088 simple_qa answering 1376.7839999999935 2576 1292 1.9938080495356036 3 0 0 True
191 simple_qa_00089 simple_qa answering 727.212999999999 5616 1291 4.350116189000775 3 0 0 True
192 simple_qa_00090 simple_qa answering 1237.8660000000039 7402 851 8.698002350176264 3 0 0 True
193 simple_qa_00091 simple_qa answering 757.8150000000007 9526 1514 6.291941875825628 5 1 0 True
194 simple_qa_00092 simple_qa answering 2362.844000000003 4959 1026 4.833333333333333 3 0 0 True
195 simple_qa_00093 simple_qa answering 1152.037 4596 920 4.995652173913044 3 0 0 True
196 simple_qa_00094 simple_qa answering 1841.4469999999951 4404 1581 2.7855787476280836 3 0 0 True
197 simple_qa_00095 simple_qa answering 1221.4370000000017 5886 1182 4.979695431472082 3 0 0 True
198 simple_qa_00096 simple_qa answering 1167.4190000000024 5641 2854 1.9765241765942536 3 0 0 True
199 simple_qa_00097 simple_qa answering 1575.9909999999948 4913 1439 3.414176511466296 3 0 0 True
200 simple_qa_00098 simple_qa answering 1244.641999999999 8507 1101 7.72661217075386 3 0 0 True
201 simple_qa_00099 simple_qa answering 1048.887999999998 4661 1839 2.5345296356715608 3 0 0 True
202 tool_research_00000 tool_research evidence_collection 2194.9050000000057 24867 3202 7.766083697688944 5 1 0 True
203 tool_research_00001 tool_research evidence_collection 3702.2710000000034 43758 1917 22.826291079812208 9 2 0 True
204 tool_research_00002 tool_research evidence_collection 4914.04399999999 29867 1906 15.669989506820567 5 1 0 True
205 tool_research_00003 tool_research evidence_collection 2975.851999999996 18814 4275 4.40093567251462 5 1 0 True
206 tool_research_00004 tool_research evidence_collection 1859.4280000000012 17926 1263 14.193190815518607 3 0 0 True
207 tool_research_00005 tool_research evidence_collection 1666.4189999999976 13686 8729 1.56787719097262 5 1 0 True
208 tool_research_00006 tool_research evidence_collection 2696.655000000007 9331 1703 5.479154433352907 3 0 0 True
209 tool_research_00007 tool_research evidence_collection 5450.783000000001 13849 1654 8.373035066505441 6 2 1 True
210 tool_research_00008 tool_research evidence_collection 1531.513000000004 17238 3296 5.22997572815534 5 1 0 True
211 tool_research_00009 tool_research evidence_collection 4081.8340000000007 13926 436 31.940366972477065 5 1 0 True
212 tool_research_00010 tool_research evidence_collection 4327.119000000011 41953 2235 18.770917225950782 5 1 0 True
213 tool_research_00011 tool_research evidence_collection 3781.2230000000113 15091 3794 3.977596204533474 5 1 0 True
214 tool_research_00012 tool_research evidence_collection 1917.4310000000078 14626 1784 8.198430493273543 3 0 0 True
215 tool_research_00013 tool_research evidence_collection 3997.425000000007 13485 1603 8.412351840299438 5 1 0 True
216 tool_research_00014 tool_research evidence_collection 2441.9809999999984 36453 2047 17.80801172447484 5 1 0 True
217 tool_research_00015 tool_research evidence_collection 3959.5280000000057 15873 1390 11.419424460431655 3 0 0 True
218 tool_research_00016 tool_research evidence_collection 1198.003 13816 976 14.155737704918034 3 0 0 True
219 tool_research_00017 tool_research evidence_collection 4552.255999999999 16333 2462 6.634037367993502 5 1 0 True
220 tool_research_00018 tool_research evidence_collection 6950.037999999992 39260 5865 6.693947144075021 6 2 1 True
221 tool_research_00019 tool_research evidence_collection 3067.522999999994 15009 2037 7.368188512518409 3 0 0 True
222 tool_research_00020 tool_research evidence_collection 4835.037999999997 30787 1662 18.524067388688326 7 1 0 True
223 tool_research_00021 tool_research evidence_collection 8310.215999999997 113647 4305 26.39883855981417 17 4 0 True
224 tool_research_00022 tool_research evidence_collection 3200.504999999993 18179 1048 17.346374045801525 5 1 0 True
225 tool_research_00023 tool_research evidence_collection 13355.828000000003 126809 1205 105.2356846473029 15 5 1 True
226 tool_research_00024 tool_research evidence_collection 3643.411999999998 21779 2025 10.755061728395061 5 1 0 True
227 tool_research_00025 tool_research evidence_collection 9670.201000000006 47663 1365 34.91794871794872 13 4 2 True
228 tool_research_00026 tool_research evidence_collection 1291.9939999999883 12623 3997 3.1581185889417065 3 0 0 True
229 tool_research_00027 tool_research evidence_collection 4673.997999999998 27499 1513 18.17514871116986 5 1 0 True
230 tool_research_00028 tool_research evidence_collection 2161.7999999999993 32414 1401 23.13633119200571 5 1 0 True
231 tool_research_00029 tool_research evidence_collection 5903.75499999999 21437 3963 5.40928589452435 5 1 0 True
232 tool_research_00030 tool_research evidence_collection 4832.2890000000025 62170 2517 24.70003972983711 9 2 0 True
233 tool_research_00031 tool_research evidence_collection 4330.880000000007 29507 2884 10.23127600554785 6 2 1 True
234 tool_research_00032 tool_research evidence_collection 1570.5789999999952 18174 849 21.406360424028268 5 1 0 True
235 tool_research_00033 tool_research evidence_collection 1797.4840000000113 34726 2226 15.600179694519317 5 1 0 True
236 tool_research_00034 tool_research evidence_collection 3040.871999999993 19123 2094 9.13228271251194 5 1 0 True
237 tool_research_00035 tool_research evidence_collection 2986.626000000001 24572 1303 18.858019953952418 5 1 0 True
238 tool_research_00036 tool_research evidence_collection 3130.6490000000053 28061 1577 17.793912492073556 3 0 0 True
239 tool_research_00037 tool_research evidence_collection 3123.7370000000055 22728 3665 6.201364256480218 5 1 0 True
240 tool_research_00038 tool_research evidence_collection 1708.3070000000048 29910 1078 27.74582560296846 5 1 0 True
241 tool_research_00039 tool_research evidence_collection 4255.195999999998 21270 1412 15.063739376770538 5 1 0 True
242 tool_research_00040 tool_research evidence_collection 2188.941 24341 4087 5.955713237093223 5 1 0 True
243 tool_research_00041 tool_research evidence_collection 2437.484999999995 4248 1853 2.2924986508364813 3 0 0 True
244 tool_research_00042 tool_research evidence_collection 2187.698999999995 8817 2395 3.681419624217119 3 0 0 True
245 tool_research_00043 tool_research evidence_collection 5124.787999999995 36771 2156 17.055194805194805 9 2 0 True
246 tool_research_00044 tool_research evidence_collection 2136.277000000007 23014 3951 5.824854467223488 5 1 0 True
247 tool_research_00045 tool_research evidence_collection 2712.2329999999974 13715 4904 2.7966965742251224 5 1 0 True
248 tool_research_00046 tool_research evidence_collection 2093.755999999999 27149 2497 10.872647176611935 3 0 0 True
249 tool_research_00047 tool_research evidence_collection 3331.8359999999957 10694 2450 4.364897959183674 3 0 0 True
250 tool_research_00048 tool_research evidence_collection 2496.739000000005 23797 420 56.65952380952381 5 1 0 True
251 tool_research_00049 tool_research evidence_collection 3162.072999999992 37174 6914 5.376627133352618 5 1 0 True
252 tool_research_00050 tool_research evidence_collection 3349.9610000000075 20453 1503 13.608117099135063 5 1 0 True
253 tool_research_00051 tool_research evidence_collection 2585.735999999997 20752 4970 4.175452716297786 5 1 0 True
254 tool_research_00052 tool_research evidence_collection 2241.700999999992 18226 1014 17.974358974358974 5 1 0 True
255 tool_research_00053 tool_research evidence_collection 1681.621000000007 20527 1964 10.451629327902241 5 1 0 True
256 tool_research_00054 tool_research evidence_collection 4616.5809999999965 14793 1020 14.50294117647059 5 1 0 True
257 tool_research_00055 tool_research evidence_collection 1986.9599999999964 36674 1499 24.46564376250834 5 1 0 True
258 tool_research_00056 tool_research evidence_collection 3329.991000000007 21611 2138 10.108044901777362 5 1 0 True
259 tool_research_00057 tool_research evidence_collection 1935.023000000001 11508 3856 2.9844398340248963 3 0 0 True
260 tool_research_00058 tool_research evidence_collection 2901.527999999999 31197 1663 18.759470835838844 5 1 0 True
261 tool_research_00059 tool_research evidence_collection 3321.638000000007 11370 816 13.933823529411764 3 0 0 True
262 tool_research_00060 tool_research evidence_collection 3683.4269999999947 22492 1908 11.78825995807128 5 1 0 True
263 tool_research_00061 tool_research evidence_collection 2848.731999999998 18988 1760 10.788636363636364 5 1 0 True
264 tool_research_00062 tool_research evidence_collection 2672.6560000000036 11461 1837 6.238976592270006 5 1 0 True
265 tool_research_00063 tool_research evidence_collection 2669.6290000000004 12186 2987 4.079678607298293 3 0 0 True
266 tool_research_00064 tool_research evidence_collection 1733.4749999999985 20624 2281 9.041648399824638 5 1 0 True
267 tool_research_00065 tool_research evidence_collection 1969.7800000000002 37289 2064 18.066375968992247 5 1 0 True
268 tool_research_00066 tool_research evidence_collection 2515.674000000004 27763 948 29.285864978902953 5 1 0 True
269 tool_research_00067 tool_research evidence_collection 3096.862999999999 25812 1096 23.55109489051095 5 1 0 True
270 tool_research_00068 tool_research evidence_collection 2049.244999999999 27451 1646 16.677399756986635 5 1 0 True
271 tool_research_00069 tool_research evidence_collection 1731.0909999999922 25997 2954 8.800609343263371 5 1 0 True
272 tool_research_00070 tool_research evidence_collection 3312.636999999995 31567 3135 10.069218500797447 5 1 0 True
273 tool_research_00071 tool_research evidence_collection 1862.328000000005 20908 2780 7.520863309352518 5 1 0 True
274 tool_research_00072 tool_research evidence_collection 3047.896000000009 54132 1025 52.81170731707317 5 1 0 True
275 tool_research_00073 tool_research evidence_collection 2561.8630000000026 21435 4790 4.474947807933194 5 1 0 True
276 tool_research_00074 tool_research evidence_collection 4560.357999999994 79773 2385 33.44779874213837 13 3 0 True
277 tool_research_00075 tool_research evidence_collection 3243.395000000007 7843 2993 2.6204477113264284 3 0 0 True
278 tool_research_00076 tool_research evidence_collection 2738.9289999999987 23031 2795 8.240071556350626 5 1 0 True
279 tool_research_00077 tool_research evidence_collection 5143.501999999998 26921 3689 7.297641637300082 3 0 0 True
280 tool_research_00078 tool_research evidence_collection 2541.331999999997 10770 5383 2.000743080066877 3 0 0 True
281 tool_research_00079 tool_research evidence_collection 4596.682000000002 30560 3128 9.769820971867007 9 2 0 True
282 tool_research_00080 tool_research evidence_collection 2516.4350000000013 10007 1693 5.910809214412286 3 0 0 True
283 tool_research_00081 tool_research evidence_collection 3084.7260000000033 17944 830 21.619277108433735 5 1 0 True
284 tool_research_00082 tool_research evidence_collection 2914.749999999998 25400 982 25.865580448065174 5 1 0 True
285 tool_research_00083 tool_research evidence_collection 2230.4889999999914 24604 2144 11.475746268656716 5 1 0 True
286 tool_research_00084 tool_research evidence_collection 3443.204000000009 24850 739 33.62652232746955 5 1 0 True
287 tool_research_00085 tool_research evidence_collection 5764.497000000006 31697 6531 4.853314959424284 6 2 1 True
288 tool_research_00086 tool_research evidence_collection 2663.731999999996 14968 967 15.478800413650465 5 1 0 True
289 tool_research_00087 tool_research evidence_collection 1660.2049999999906 10680 3250 3.286153846153846 5 1 0 True
290 tool_research_00088 tool_research evidence_collection 1999.1580000000085 11601 3306 3.5090744101633393 3 0 0 True
291 tool_research_00089 tool_research evidence_collection 2695.4450000000065 10711 3265 3.280551301684533 5 1 0 True
292 tool_research_00090 tool_research evidence_collection 5276.9389999999985 15851 1980 8.005555555555556 5 1 0 True
293 tool_research_00091 tool_research evidence_collection 5764.26699999999 27062 2151 12.581125058112505 6 2 1 True
294 tool_research_00092 tool_research evidence_collection 1482.0979999999936 17916 936 19.141025641025642 5 1 0 True
295 tool_research_00093 tool_research evidence_collection 2160.2140000000104 36749 2052 17.908869395711502 5 1 0 True
296 tool_research_00094 tool_research evidence_collection 3420.692000000017 15674 8252 1.8994183228308288 3 0 0 True
297 tool_research_00095 tool_research evidence_collection 1882.05099999999 19776 2123 9.315120113047573 5 1 0 True
298 tool_research_00096 tool_research evidence_collection 3586.549000000005 36710 1309 28.044308632543927 5 1 0 True
299 tool_research_00097 tool_research evidence_collection 1987.364999999997 14435 3124 4.62067861715749 5 1 0 True
300 tool_research_00098 tool_research evidence_collection 3917.211000000009 16232 1378 11.779390420899855 6 2 1 True
301 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
1 timeout_probability max_retries success_rate mean_retries mean_amplification mean_latency_ms
2 0.0 0 1.0 0.0 9.791625846103754 1611.6456398964472
3 0.0 1 1.0 0.0 9.929872318854873 1810.7223041670222
4 0.0 2 1.0 0.0 8.566505830883267 1646.5055480731012
5 0.0 3 1.0 0.0 9.466712608627542 1652.6593639522055
6 0.0 5 1.0 0.0 9.662682945914268 1756.6494872943697
7 0.03 0 0.9625 0.0 9.236763247092442 1764.2494023015984
8 0.03 1 1.0 0.016666666666666666 9.49838873538483 1668.745910772185
9 0.03 2 1.0 0.0375 9.40180231370975 1753.199216159701
10 0.03 3 1.0 0.016666666666666666 10.022457643868133 1860.8835997078063
11 0.03 5 1.0 0.025 9.019935163210244 1900.697800739017
12 0.08 0 0.9291666666666667 0.0 9.92154310687105 1719.1310133789257
13 0.08 1 0.9958333333333333 0.05416666666666667 9.48779578533714 1843.49537077021
14 0.08 2 0.9958333333333333 0.07083333333333333 9.542258282931957 1902.6419815786642
15 0.08 3 1.0 0.05 9.887456874772154 1817.7727139655656
16 0.08 5 1.0 0.09166666666666666 9.097284092135592 1904.8547916418988
17 0.15 0 0.8541666666666666 0.0 8.835720371687312 1571.6219931658118
18 0.15 1 0.9791666666666666 0.09583333333333334 9.122618265595515 1955.8897478710594
19 0.15 2 1.0 0.10833333333333334 9.846728400807162 1980.994814000937
20 0.15 3 1.0 0.12083333333333333 9.51555007863001 1950.3948320063673
21 0.15 5 1.0 0.19166666666666668 10.257406318574677 2173.315967936333
22 0.25 0 0.8333333333333334 0.0 8.62914384683803 1654.824555364319
23 0.25 1 0.9541666666666667 0.16666666666666666 8.984142037708278 2090.160252075161
24 0.25 2 0.9875 0.2625 9.642823436259429 2393.4294606209505
25 0.25 3 1.0 0.22916666666666666 8.7946687060034 2226.263869969628
26 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
1 arrival_rate offered_tasks completed_tasks throughput_per_second mean_delay_ms p95_delay_ms queue_peak drop_rate success_rate mean_amplification
2 0.5 98 85 0.53125 5789.822235500761 12757.162733844745 5 0.0 1.0 31.470196724444556
3 1.0 176 160 1.0 31384.496417526076 42781.94943988779 34 0.0 1.0 31.986629448479086
4 2.0 352 317 1.98125 153100.48173718844 266221.0600580607 211 0.0 0.9968454258675079 27.062374263992844
5 4.0 687 574 3.5875 371545.11383159773 654462.4416805771 500 0.06841339155749636 1.0 32.343350031249344
6 6.0 1095 518 3.2375 403282.1583010225 624405.7892324593 500 0.410958904109589 0.9980694980694981 28.847411906142742
7 8.0 1433 477 2.98125 453122.6068650545 634995.5685232729 500 0.5422191207257502 1.0 28.88759065286518
8 10.0 1829 465 2.90625 460685.0783967892 629246.0471832517 500 0.644614543466375 0.9978494623655914 29.343167280152798
9 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
1 model metric mae rmse mape_percent
2 full_model internal_bytes 8514.790993271408 10202.035682525451 25.132613550059535
3 full_model latency_ms 1740.55513184213 2061.3161939037764 42.13888590021146
4 full_model message_count 0.24833333333333366 0.34639011404933506 4.4460827599229225
5 full_model tool_calls 0.0977777777777778 0.12750453877179202 8.967944987269812
6 full_model amplification 2.1844309474987855 3.1463454795356744 17.403062466244346
7 no_context internal_bytes 28106.101475356598 38300.17877551533 107.12005537801083
8 no_context latency_ms 3059.4684226124723 4030.5538811505185 68.83144127074493
9 no_context message_count 2.332777777777778 3.1734000051352798 34.22052281701404
10 no_context tool_calls 0.645 0.7287946670130528 188.58078578942232
11 no_context amplification 10.861414695027626 13.961977843833159 67.33834604907454
12 static_mean internal_bytes 29834.93333333333 32709.783175317236 230.39064998346973
13 static_mean latency_ms 2757.6886622222223 3058.6901465213614 119.58343818448623
14 static_mean message_count 2.5155555555555558 2.7855500155066126 48.03496553983882
15 static_mean tool_calls 0.5444444444444444 0.6355225321645873 264.95059144468667
16 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
1 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
2 collaborative_analysis static_mean 82782.45 38030.049999999996 8428.771760000001 4292.238766666668 9.88 6.1066666666666665 1.66 0.9266666666666667 33.798140646040636 17.719989109017618
3 collaborative_analysis no_context 82782.45 17953.655088125477 8428.771760000001 1674.760201302985 9.88 4.575 1.66 0.55 33.798140646040636 10.538207426716697
4 collaborative_analysis full_model 82782.45 68099.5326730428 8428.771760000001 5276.731101216728 9.88 9.741666666666667 1.66 1.75 33.798140646040636 33.290090674565
5 simple_qa static_mean 5514.23 38030.049999999996 1128.43623 4292.238766666668 3.24 6.1066666666666665 0.11 0.9266666666666667 4.875984197964249 17.719989109017618
6 simple_qa no_context 5514.23 17261.226304896398 1128.43623 2040.1508029795593 3.24 4.65 0.11 0.625 4.875984197964249 9.934747754184363
7 simple_qa full_model 5514.23 4423.486362645099 1128.43623 672.4328817972068 3.24 3.216666666666667 0.11 0.10833333333333334 4.875984197964249 4.216398328357828
8 tool_research static_mean 25793.47 38030.049999999996 3319.5083100000024 4292.238766666668 5.2 6.1066666666666665 1.01 0.9266666666666667 14.485842483047964 17.719989109017618
9 tool_research no_context 25793.47 18050.956790701126 3319.5083100000024 1806.829173839162 5.2 4.916666666666667 1.01 0.7 14.485842483047964 10.22029517350914
10 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
1 task_id task_type task_phase latency_ms internal_bytes input_bytes amplification message_count tool_calls retries success
2 collaborative_analysis_00000 collaborative_analysis multi_agent_synthesis 6111.839000000004 62448 1205 51.824066390041494 7 1 0 True
3 collaborative_analysis_00001 collaborative_analysis multi_agent_synthesis 7858.875999999981 57236 2452 23.34257748776509 7 0 0 True
4 collaborative_analysis_00002 collaborative_analysis multi_agent_synthesis 3745.010999999977 36184 6916 5.231925968768074 5 1 0 True
5 collaborative_analysis_00003 collaborative_analysis multi_agent_synthesis 3370.6700000000183 15600 1146 13.612565445026178 3 0 0 True
6 collaborative_analysis_00004 collaborative_analysis multi_agent_synthesis 3970.753000000002 26927 5695 4.728182616330114 5 1 0 True
7 collaborative_analysis_00005 collaborative_analysis multi_agent_synthesis 3692.181000000005 9783 2845 3.438664323374341 3 0 0 True
8 collaborative_analysis_00006 collaborative_analysis multi_agent_synthesis 12027.614 101344 5088 19.91823899371069 9 1 0 True
9 collaborative_analysis_00007 collaborative_analysis multi_agent_synthesis 3174.7689999999975 13427 10177 1.3193475483934363 3 0 0 True
10 collaborative_analysis_00008 collaborative_analysis multi_agent_synthesis 4553.435000000008 106516 5924 17.98041863605672 13 2 0 True
11 collaborative_analysis_00009 collaborative_analysis multi_agent_synthesis 20393.187000000013 136393 8870 15.376888387824126 19 3 0 True
12 collaborative_analysis_00010 collaborative_analysis multi_agent_synthesis 9716.779000000002 43830 1420 30.866197183098592 9 2 0 True
13 collaborative_analysis_00011 collaborative_analysis multi_agent_synthesis 13658.126999999979 113877 6803 16.73923269145965 13 2 0 True
14 collaborative_analysis_00012 collaborative_analysis multi_agent_synthesis 5092.640999999986 138420 4391 31.523570940560237 13 2 0 True
15 collaborative_analysis_00013 collaborative_analysis multi_agent_synthesis 2393.601999999987 13198 8494 1.5538026842477042 3 0 0 True
16 collaborative_analysis_00014 collaborative_analysis multi_agent_synthesis 7330.83400000001 65750 876 75.05707762557077 11 2 0 True
17 collaborative_analysis_00015 collaborative_analysis multi_agent_synthesis 16492.502 180400 2157 83.63467779323133 23 3 0 True
18 collaborative_analysis_00016 collaborative_analysis multi_agent_synthesis 16875.831000000006 205302 2605 78.81074856046065 19 3 0 True
19 collaborative_analysis_00017 collaborative_analysis multi_agent_synthesis 9850.209000000006 147782 1988 74.33702213279678 19 3 0 True
20 collaborative_analysis_00018 collaborative_analysis multi_agent_synthesis 10007.738999999987 126126 4218 29.90184921763869 15 2 0 True
21 collaborative_analysis_00019 collaborative_analysis multi_agent_synthesis 11525.198999999986 106483 1192 89.33137583892618 7 1 0 True
22 collaborative_analysis_00020 collaborative_analysis multi_agent_synthesis 5159.906000000006 59557 2210 26.94886877828054 9 2 0 True
23 collaborative_analysis_00021 collaborative_analysis multi_agent_synthesis 4791.642999999994 57467 18445 3.1155868799132556 5 0 0 True
24 collaborative_analysis_00022 collaborative_analysis multi_agent_synthesis 11351.583000000006 75128 3315 22.663046757164405 9 1 0 True
25 collaborative_analysis_00023 collaborative_analysis multi_agent_synthesis 8277.253999999999 39603 5217 7.591144335825187 5 1 0 True
26 collaborative_analysis_00024 collaborative_analysis multi_agent_synthesis 19919.341000000004 167247 1166 143.43653516295026 23 5 0 True
27 collaborative_analysis_00025 collaborative_analysis multi_agent_synthesis 9099.73500000001 69536 6843 10.161625018266841 11 1 0 True
28 collaborative_analysis_00026 collaborative_analysis multi_agent_synthesis 3098.5450000000014 55189 7507 7.351671773011856 11 2 0 True
29 collaborative_analysis_00027 collaborative_analysis multi_agent_synthesis 6933.150000000012 128239 5952 21.545530913978496 13 3 0 True
30 collaborative_analysis_00028 collaborative_analysis multi_agent_synthesis 14684.41899999999 164414 1446 113.70262793914246 18 5 1 True
31 collaborative_analysis_00029 collaborative_analysis multi_agent_synthesis 22606.593000000004 130445 2700 48.31296296296296 13 3 2 True
32 collaborative_analysis_00030 collaborative_analysis multi_agent_synthesis 7566.215999999997 53530 2840 18.848591549295776 7 0 0 True
33 collaborative_analysis_00031 collaborative_analysis multi_agent_synthesis 9549.07 182717 560 326.28035714285716 11 2 0 True
34 collaborative_analysis_00032 collaborative_analysis multi_agent_synthesis 16413.354 140512 4336 32.40590405904059 13 1 0 True
35 collaborative_analysis_00033 collaborative_analysis multi_agent_synthesis 3107.8390000000127 25062 1526 16.42332896461337 3 0 0 True
36 collaborative_analysis_00034 collaborative_analysis multi_agent_synthesis 2382.689999999997 37813 4410 8.57437641723356 5 1 0 True
37 collaborative_analysis_00035 collaborative_analysis multi_agent_synthesis 6573.08900000001 42752 1231 34.72948822095857 9 2 0 True
38 collaborative_analysis_00036 collaborative_analysis multi_agent_synthesis 14503.11400000001 179234 7724 23.20481615743138 23 6 1 True
39 collaborative_analysis_00037 collaborative_analysis multi_agent_synthesis 6998.415999999992 40737 4407 9.243703199455412 5 1 0 True
40 collaborative_analysis_00038 collaborative_analysis multi_agent_synthesis 9218.387000000006 76646 5615 13.650222617987533 12 3 1 True
41 collaborative_analysis_00039 collaborative_analysis multi_agent_synthesis 14171.648999999974 82798 3958 20.919151086407275 13 2 0 True
42 collaborative_analysis_00040 collaborative_analysis multi_agent_synthesis 16203.926999999992 192384 4272 45.03370786516854 19 2 0 True
43 collaborative_analysis_00041 collaborative_analysis multi_agent_synthesis 8077.832999999999 86864 14703 5.907909950350269 9 1 0 True
44 collaborative_analysis_00042 collaborative_analysis multi_agent_synthesis 11980.147000000017 175669 4129 42.545168321627514 17 2 0 True
45 collaborative_analysis_00043 collaborative_analysis multi_agent_synthesis 8383.41299999999 86553 4556 18.99758560140474 11 1 0 True
46 collaborative_analysis_00044 collaborative_analysis multi_agent_synthesis 3781.3569999999854 21537 2248 9.580516014234876 5 1 0 True
47 collaborative_analysis_00045 collaborative_analysis multi_agent_synthesis 2871.480999999989 29178 3997 7.299974981235927 5 1 0 True
48 collaborative_analysis_00046 collaborative_analysis multi_agent_synthesis 1987.737999999979 21361 8073 2.6459804285891244 3 0 0 True
49 collaborative_analysis_00047 collaborative_analysis multi_agent_synthesis 10075.866999999987 219312 9941 22.061362036012472 17 3 0 True
50 collaborative_analysis_00048 collaborative_analysis multi_agent_synthesis 6179.957999999999 70354 2470 28.4834008097166 5 1 0 True
51 collaborative_analysis_00049 collaborative_analysis multi_agent_synthesis 3145.8080000000164 28609 4669 6.127436281859071 3 0 0 True
52 collaborative_analysis_00050 collaborative_analysis multi_agent_synthesis 6249.4649999999865 28317 882 32.105442176870746 7 1 0 True
53 collaborative_analysis_00051 collaborative_analysis multi_agent_synthesis 11702.425000000005 187198 1275 146.82196078431372 17 2 0 True
54 collaborative_analysis_00052 collaborative_analysis multi_agent_synthesis 10426.145999999988 122179 1403 87.08410548823949 13 2 0 True
55 collaborative_analysis_00053 collaborative_analysis multi_agent_synthesis 3776.5890000000013 10701 3073 3.482264887731858 3 0 0 True
56 collaborative_analysis_00054 collaborative_analysis multi_agent_synthesis 6411.059999999992 122716 3644 33.6761800219539 13 3 0 True
57 collaborative_analysis_00055 collaborative_analysis multi_agent_synthesis 9190.782999999981 87827 8202 10.707998049256279 13 1 0 True
58 collaborative_analysis_00056 collaborative_analysis multi_agent_synthesis 26072.79299999999 196393 2732 71.88616398243046 22 5 1 True
59 collaborative_analysis_00057 collaborative_analysis multi_agent_synthesis 6656.256000000013 33081 7347 4.502654144548796 7 1 0 True
60 collaborative_analysis_00058 collaborative_analysis multi_agent_synthesis 5274.61199999999 58229 9303 6.259163710630979 8 2 1 True
61 collaborative_analysis_00059 collaborative_analysis multi_agent_synthesis 5612.335999999999 17516 7543 2.3221529895267135 3 0 0 True
62 collaborative_analysis_00060 collaborative_analysis multi_agent_synthesis 7323.184999999995 88159 6584 13.389884568651276 5 1 0 True
63 collaborative_analysis_00061 collaborative_analysis multi_agent_synthesis 13041.410999999982 39582 4651 8.510427864975274 5 0 0 True
64 collaborative_analysis_00062 collaborative_analysis multi_agent_synthesis 5737.938000000014 55676 4041 13.777777777777779 11 2 0 True
65 collaborative_analysis_00063 collaborative_analysis multi_agent_synthesis 13871.848999999998 111676 5758 19.39492879472039 18 5 1 True
66 collaborative_analysis_00064 collaborative_analysis multi_agent_synthesis 14159.884000000005 93620 743 126.00269179004037 11 2 0 True
67 collaborative_analysis_00065 collaborative_analysis multi_agent_synthesis 2143.2680000000064 44223 2414 18.319386909693456 5 0 0 True
68 collaborative_analysis_00066 collaborative_analysis multi_agent_synthesis 9103.234999999984 120161 2301 52.22120817036071 11 0 0 True
69 collaborative_analysis_00067 collaborative_analysis multi_agent_synthesis 7975.786999999997 51818 2211 23.43645409317051 9 2 0 True
70 collaborative_analysis_00068 collaborative_analysis multi_agent_synthesis 10306.556999999997 143550 1168 122.90239726027397 15 3 0 True
71 collaborative_analysis_00069 collaborative_analysis multi_agent_synthesis 10491.949999999975 88142 1034 85.24371373307544 13 3 0 True
72 collaborative_analysis_00070 collaborative_analysis multi_agent_synthesis 5671.043999999994 92836 4373 21.229361994054425 7 1 0 True
73 collaborative_analysis_00071 collaborative_analysis multi_agent_synthesis 2233.918000000017 35792 908 39.418502202643175 5 1 0 True
74 collaborative_analysis_00072 collaborative_analysis multi_agent_synthesis 2779.2799999999997 19132 1140 16.782456140350877 3 0 0 True
75 collaborative_analysis_00073 collaborative_analysis multi_agent_synthesis 5933.890999999989 53137 2409 22.057700290577003 7 1 0 True
76 collaborative_analysis_00074 collaborative_analysis multi_agent_synthesis 11494.603000000012 198018 8671 22.836812363049244 15 5 1 True
77 collaborative_analysis_00075 collaborative_analysis multi_agent_synthesis 3800.8010000000068 92249 1891 48.78318350079323 7 0 0 True
78 collaborative_analysis_00076 collaborative_analysis multi_agent_synthesis 15271.408000000009 110064 4836 22.759305210918114 13 4 2 True
79 collaborative_analysis_00077 collaborative_analysis multi_agent_synthesis 3524.1379999999936 49633 2359 21.03984739296312 7 0 0 True
80 collaborative_analysis_00078 collaborative_analysis multi_agent_synthesis 1085.5840000000114 34459 1481 23.267386900742743 3 0 0 True
81 collaborative_analysis_00079 collaborative_analysis multi_agent_synthesis 3396.9510000000014 7311 4899 1.492345376607471 3 0 0 True
82 collaborative_analysis_00080 collaborative_analysis multi_agent_synthesis 7375.2580000000025 40747 2612 15.599923430321592 10 3 1 True
83 collaborative_analysis_00081 collaborative_analysis multi_agent_synthesis 11392.599000000018 125175 5129 24.405342171963344 17 5 1 True
84 collaborative_analysis_00082 collaborative_analysis multi_agent_synthesis 4221.8009999999995 46903 1193 39.3151718357083 3 0 0 True
85 collaborative_analysis_00083 collaborative_analysis multi_agent_synthesis 4469.9559999999965 34392 7835 4.389534141671985 5 0 0 True
86 collaborative_analysis_00084 collaborative_analysis multi_agent_synthesis 14913.923000000012 148982 4218 35.32053105737316 17 5 2 False
87 collaborative_analysis_00085 collaborative_analysis multi_agent_synthesis 3174.0640000000158 26574 2863 9.281872162067762 3 0 0 True
88 collaborative_analysis_00086 collaborative_analysis multi_agent_synthesis 6104.687000000013 29578 2252 13.134103019538188 6 2 1 True
89 collaborative_analysis_00087 collaborative_analysis multi_agent_synthesis 3079.0619999999935 23392 7001 3.3412369661476933 3 0 0 True
90 collaborative_analysis_00088 collaborative_analysis multi_agent_synthesis 15710.582000000017 123812 1087 113.90248390064397 17 3 0 True
91 collaborative_analysis_00089 collaborative_analysis multi_agent_synthesis 9594.03499999999 123841 7467 16.585107807687155 15 3 0 True
92 collaborative_analysis_00090 collaborative_analysis multi_agent_synthesis 8018.177000000009 35223 2432 14.483141447368421 7 1 0 True
93 collaborative_analysis_00091 collaborative_analysis multi_agent_synthesis 8070.577999999983 85639 1800 47.577222222222225 9 1 0 True
94 collaborative_analysis_00092 collaborative_analysis multi_agent_synthesis 6954.7670000000035 30543 2606 11.720260936300845 8 2 1 True
95 collaborative_analysis_00093 collaborative_analysis multi_agent_synthesis 2334.4150000000072 9761 1259 7.75297855440826 3 0 0 True
96 collaborative_analysis_00094 collaborative_analysis multi_agent_synthesis 3988.2240000000024 53918 4052 13.306515301085884 7 0 0 True
97 collaborative_analysis_00095 collaborative_analysis multi_agent_synthesis 6538.421999999997 67526 4362 15.480513525905549 7 1 0 True
98 collaborative_analysis_00096 collaborative_analysis multi_agent_synthesis 7050.077000000016 89764 5545 16.188277727682596 9 0 0 True
99 collaborative_analysis_00097 collaborative_analysis multi_agent_synthesis 14613.135 138234 1905 72.56377952755905 18 4 1 True
100 collaborative_analysis_00098 collaborative_analysis multi_agent_synthesis 5859.162999999995 34186 15338 2.2288433954883295 6 2 1 True
101 collaborative_analysis_00099 collaborative_analysis multi_agent_synthesis 17759.783999999996 169187 11129 15.202354209722348 21 5 0 True
102 simple_qa_00000 simple_qa answering 855.1170000000001 3448 2896 1.1906077348066297 3 0 0 True
103 simple_qa_00001 simple_qa answering 1403.896 4962 1531 3.24101894186806 3 0 0 True
104 simple_qa_00002 simple_qa answering 1171.8220000000001 4350 787 5.527318932655654 3 0 0 True
105 simple_qa_00003 simple_qa answering 1504.4239999999998 2494 375 6.650666666666667 3 0 0 True
106 simple_qa_00004 simple_qa answering 1963.5280000000002 5963 591 10.089678510998308 5 1 0 True
107 simple_qa_00005 simple_qa answering 1452.445 5943 2101 2.8286530223703 3 0 0 True
108 simple_qa_00006 simple_qa answering 825.0729999999998 3757 1209 3.10752688172043 3 0 0 True
109 simple_qa_00007 simple_qa answering 926.895 3668 2132 1.7204502814258913 3 0 0 True
110 simple_qa_00008 simple_qa answering 1005.903 4694 1529 3.0699803793328972 3 0 0 True
111 simple_qa_00009 simple_qa answering 1038.875 5016 1632 3.073529411764706 3 0 0 True
112 simple_qa_00010 simple_qa answering 659.4789999999992 9518 859 11.080325960419092 3 0 0 True
113 simple_qa_00011 simple_qa answering 1125.273 3965 1038 3.8198458574181116 3 0 0 True
114 simple_qa_00012 simple_qa answering 1077.1380000000015 5386 1219 4.418375717801476 3 0 0 True
115 simple_qa_00013 simple_qa answering 1004.5659999999988 5660 889 6.366704161979753 3 0 0 True
116 simple_qa_00014 simple_qa answering 996.1830000000002 4420 1161 3.8070628768303187 3 0 0 True
117 simple_qa_00015 simple_qa answering 860.6720000000009 4252 1484 2.8652291105121295 3 0 0 True
118 simple_qa_00016 simple_qa answering 781.1749999999993 6704 1189 5.638351555929352 3 0 0 True
119 simple_qa_00017 simple_qa answering 700.6979999999992 4185 1526 2.7424639580602883 3 0 0 True
120 simple_qa_00018 simple_qa answering 1115.2699999999988 5439 1075 5.05953488372093 3 0 0 True
121 simple_qa_00019 simple_qa answering 850.3690000000006 3539 1636 2.16320293398533 3 0 0 True
122 simple_qa_00020 simple_qa answering 823.193999999999 5658 1063 5.322671683913453 3 0 0 True
123 simple_qa_00021 simple_qa answering 930.963000000002 6726 2009 3.3479342956694875 3 0 0 True
124 simple_qa_00022 simple_qa answering 742.083000000001 5048 1822 2.770581778265642 3 0 0 True
125 simple_qa_00023 simple_qa answering 1172.7469999999976 3674 1567 2.3446075303126994 3 0 0 True
126 simple_qa_00024 simple_qa answering 604.9790000000002 7257 1006 7.213717693836978 3 0 0 True
127 simple_qa_00025 simple_qa answering 1219.6170000000031 4464 2084 2.1420345489443378 3 0 0 True
128 simple_qa_00026 simple_qa answering 753.5990000000013 4068 1755 2.317948717948718 3 0 0 True
129 simple_qa_00027 simple_qa answering 791.2379999999998 5056 1373 3.6824471959213403 3 0 0 True
130 simple_qa_00028 simple_qa answering 827.5049999999986 3795 801 4.737827715355805 3 0 0 True
131 simple_qa_00029 simple_qa answering 677.6099999999979 4655 2300 2.023913043478261 3 0 0 True
132 simple_qa_00030 simple_qa answering 791.8140000000022 4267 720 5.926388888888889 3 0 0 True
133 simple_qa_00031 simple_qa answering 1215.0280000000002 7292 3124 2.3341869398207424 5 1 0 True
134 simple_qa_00032 simple_qa answering 1804.2910000000027 4607 2837 1.6238984843144166 3 0 0 True
135 simple_qa_00033 simple_qa answering 844.0370000000001 3221 1756 1.8342824601366743 3 0 0 True
136 simple_qa_00034 simple_qa answering 1057.2420000000022 5454 1504 3.6263297872340425 3 0 0 True
137 simple_qa_00035 simple_qa answering 1576.5220000000006 5750 1500 3.8333333333333335 3 0 0 True
138 simple_qa_00036 simple_qa answering 1026.4500000000005 7409 4583 1.616626663757364 3 0 0 True
139 simple_qa_00037 simple_qa answering 716.7670000000008 5122 1777 2.8823860438942037 3 0 0 True
140 simple_qa_00038 simple_qa answering 982.6349999999984 7826 1145 6.834934497816594 3 0 0 True
141 simple_qa_00039 simple_qa answering 701.6949999999973 5078 670 7.57910447761194 3 0 0 True
142 simple_qa_00040 simple_qa answering 1318.7110000000005 5824 2164 2.6913123844731976 3 0 0 True
143 simple_qa_00041 simple_qa answering 839.9459999999976 6330 1513 4.183740912095175 3 0 0 True
144 simple_qa_00042 simple_qa answering 1454.4789999999991 5313 1358 3.9123711340206184 3 0 0 True
145 simple_qa_00043 simple_qa answering 1366.8249999999987 5530 733 7.544338335607094 3 0 0 True
146 simple_qa_00044 simple_qa answering 1134.8300000000008 5574 919 6.065288356909685 3 0 0 True
147 simple_qa_00045 simple_qa answering 1290.6880000000028 8607 1321 6.51551854655564 5 1 0 True
148 simple_qa_00046 simple_qa answering 887.5910000000005 5342 1220 4.378688524590164 3 0 0 True
149 simple_qa_00047 simple_qa answering 1500.1400000000017 11544 1496 7.716577540106952 5 0 0 True
150 simple_qa_00048 simple_qa answering 590.2030000000025 3429 1270 2.7 3 0 0 True
151 simple_qa_00049 simple_qa answering 1328.8580000000038 3926 1557 2.5215157353885678 3 0 0 True
152 simple_qa_00050 simple_qa answering 895.7130000000006 4332 1319 3.284306292645944 3 0 0 True
153 simple_qa_00051 simple_qa answering 754.6930000000032 6203 1342 4.62220566318927 3 0 0 True
154 simple_qa_00052 simple_qa answering 1541.4049999999975 5071 1117 4.539838854073411 3 0 0 True
155 simple_qa_00053 simple_qa answering 1177.0819999999985 8016 1230 6.517073170731707 5 1 0 True
156 simple_qa_00054 simple_qa answering 498.7519999999961 5493 391 14.048593350383632 3 0 0 True
157 simple_qa_00055 simple_qa answering 1162.9900000000007 7303 1651 4.423379769836463 3 0 0 True
158 simple_qa_00056 simple_qa answering 674.510000000005 2802 669 4.188340807174888 3 0 0 True
159 simple_qa_00057 simple_qa answering 2256.7659999999987 4338 969 4.476780185758514 3 0 0 True
160 simple_qa_00058 simple_qa answering 1575.8580000000038 10725 3214 3.336963285625389 5 1 0 True
161 simple_qa_00059 simple_qa answering 1815.6789999999958 5774 1265 4.564426877470356 3 0 0 True
162 simple_qa_00060 simple_qa answering 686.0010000000045 5624 923 6.0931744312026 3 0 0 True
163 simple_qa_00061 simple_qa answering 1254.2200000000037 6000 887 6.764374295377678 3 0 0 True
164 simple_qa_00062 simple_qa answering 945.3009999999936 7475 564 13.25354609929078 3 0 0 True
165 simple_qa_00063 simple_qa answering 841.0459999999987 3683 751 4.9041278295605855 3 0 0 True
166 simple_qa_00064 simple_qa answering 1241.6660000000022 9729 904 10.76216814159292 5 1 0 True
167 simple_qa_00065 simple_qa answering 1516.855999999997 6629 1109 5.977457168620378 5 1 0 True
168 simple_qa_00066 simple_qa answering 1183.698999999997 3552 1627 2.183159188690842 3 0 0 True
169 simple_qa_00067 simple_qa answering 995.9650000000054 8377 2106 3.977682811016144 3 0 0 True
170 simple_qa_00068 simple_qa answering 959.3050000000005 4731 1465 3.2293515358361775 3 0 0 True
171 simple_qa_00069 simple_qa answering 1188.1830000000023 3612 1113 3.2452830188679247 3 0 0 True
172 simple_qa_00070 simple_qa answering 1491.27 4065 761 5.341655716162943 3 0 0 True
173 simple_qa_00071 simple_qa answering 846.0699999999974 2898 1350 2.1466666666666665 3 0 0 True
174 simple_qa_00072 simple_qa answering 1207.8729999999994 3417 747 4.57429718875502 3 0 0 True
175 simple_qa_00073 simple_qa answering 1940.8279999999963 7028 3264 2.153186274509804 5 1 0 True
176 simple_qa_00074 simple_qa answering 1482.2769999999964 5076 1081 4.695652173913044 3 0 0 True
177 simple_qa_00075 simple_qa answering 864.4090000000019 6816 897 7.59866220735786 3 0 0 True
178 simple_qa_00076 simple_qa answering 1091.8100000000024 4841 1310 3.6954198473282442 3 0 0 True
179 simple_qa_00077 simple_qa answering 1149.9900000000025 4287 737 5.8168249660786975 3 0 0 True
180 simple_qa_00078 simple_qa answering 1253.6500000000003 6102 1037 5.884281581485053 3 0 0 True
181 simple_qa_00079 simple_qa answering 2618.4089999999997 6982 680 10.26764705882353 5 1 0 True
182 simple_qa_00080 simple_qa answering 838.6209999999962 5148 824 6.247572815533981 3 0 0 True
183 simple_qa_00081 simple_qa answering 706.4880000000003 8520 643 13.250388802488336 3 0 0 True
184 simple_qa_00082 simple_qa answering 1185.3399999999965 4372 474 9.223628691983123 3 0 0 True
185 simple_qa_00083 simple_qa answering 1010.4350000000011 8796 1347 6.5300668151447665 3 0 0 True
186 simple_qa_00084 simple_qa answering 652.358999999997 3394 1270 2.6724409448818895 3 0 0 True
187 simple_qa_00085 simple_qa answering 1272.1099999999979 5066 1257 4.030230708035004 3 0 0 True
188 simple_qa_00086 simple_qa answering 1247.2220000000007 7260 610 11.901639344262295 5 1 0 True
189 simple_qa_00087 simple_qa answering 813.3010000000027 3990 2088 1.910919540229885 3 0 0 True
190 simple_qa_00088 simple_qa answering 1376.7839999999935 2576 1292 1.9938080495356036 3 0 0 True
191 simple_qa_00089 simple_qa answering 727.212999999999 5616 1291 4.350116189000775 3 0 0 True
192 simple_qa_00090 simple_qa answering 1237.8660000000039 7402 851 8.698002350176264 3 0 0 True
193 simple_qa_00091 simple_qa answering 757.8150000000007 9526 1514 6.291941875825628 5 1 0 True
194 simple_qa_00092 simple_qa answering 2362.844000000003 4959 1026 4.833333333333333 3 0 0 True
195 simple_qa_00093 simple_qa answering 1152.037 4596 920 4.995652173913044 3 0 0 True
196 simple_qa_00094 simple_qa answering 1841.4469999999951 4404 1581 2.7855787476280836 3 0 0 True
197 simple_qa_00095 simple_qa answering 1221.4370000000017 5886 1182 4.979695431472082 3 0 0 True
198 simple_qa_00096 simple_qa answering 1167.4190000000024 5641 2854 1.9765241765942536 3 0 0 True
199 simple_qa_00097 simple_qa answering 1575.9909999999948 4913 1439 3.414176511466296 3 0 0 True
200 simple_qa_00098 simple_qa answering 1244.641999999999 8507 1101 7.72661217075386 3 0 0 True
201 simple_qa_00099 simple_qa answering 1048.887999999998 4661 1839 2.5345296356715608 3 0 0 True
202 tool_research_00000 tool_research evidence_collection 2194.9050000000057 24867 3202 7.766083697688944 5 1 0 True
203 tool_research_00001 tool_research evidence_collection 3702.2710000000034 43758 1917 22.826291079812208 9 2 0 True
204 tool_research_00002 tool_research evidence_collection 4914.04399999999 29867 1906 15.669989506820567 5 1 0 True
205 tool_research_00003 tool_research evidence_collection 2975.851999999996 18814 4275 4.40093567251462 5 1 0 True
206 tool_research_00004 tool_research evidence_collection 1859.4280000000012 17926 1263 14.193190815518607 3 0 0 True
207 tool_research_00005 tool_research evidence_collection 1666.4189999999976 13686 8729 1.56787719097262 5 1 0 True
208 tool_research_00006 tool_research evidence_collection 2696.655000000007 9331 1703 5.479154433352907 3 0 0 True
209 tool_research_00007 tool_research evidence_collection 5450.783000000001 13849 1654 8.373035066505441 6 2 1 True
210 tool_research_00008 tool_research evidence_collection 1531.513000000004 17238 3296 5.22997572815534 5 1 0 True
211 tool_research_00009 tool_research evidence_collection 4081.8340000000007 13926 436 31.940366972477065 5 1 0 True
212 tool_research_00010 tool_research evidence_collection 4327.119000000011 41953 2235 18.770917225950782 5 1 0 True
213 tool_research_00011 tool_research evidence_collection 3781.2230000000113 15091 3794 3.977596204533474 5 1 0 True
214 tool_research_00012 tool_research evidence_collection 1917.4310000000078 14626 1784 8.198430493273543 3 0 0 True
215 tool_research_00013 tool_research evidence_collection 3997.425000000007 13485 1603 8.412351840299438 5 1 0 True
216 tool_research_00014 tool_research evidence_collection 2441.9809999999984 36453 2047 17.80801172447484 5 1 0 True
217 tool_research_00015 tool_research evidence_collection 3959.5280000000057 15873 1390 11.419424460431655 3 0 0 True
218 tool_research_00016 tool_research evidence_collection 1198.003 13816 976 14.155737704918034 3 0 0 True
219 tool_research_00017 tool_research evidence_collection 4552.255999999999 16333 2462 6.634037367993502 5 1 0 True
220 tool_research_00018 tool_research evidence_collection 6950.037999999992 39260 5865 6.693947144075021 6 2 1 True
221 tool_research_00019 tool_research evidence_collection 3067.522999999994 15009 2037 7.368188512518409 3 0 0 True
222 tool_research_00020 tool_research evidence_collection 4835.037999999997 30787 1662 18.524067388688326 7 1 0 True
223 tool_research_00021 tool_research evidence_collection 8310.215999999997 113647 4305 26.39883855981417 17 4 0 True
224 tool_research_00022 tool_research evidence_collection 3200.504999999993 18179 1048 17.346374045801525 5 1 0 True
225 tool_research_00023 tool_research evidence_collection 13355.828000000003 126809 1205 105.2356846473029 15 5 1 True
226 tool_research_00024 tool_research evidence_collection 3643.411999999998 21779 2025 10.755061728395061 5 1 0 True
227 tool_research_00025 tool_research evidence_collection 9670.201000000006 47663 1365 34.91794871794872 13 4 2 True
228 tool_research_00026 tool_research evidence_collection 1291.9939999999883 12623 3997 3.1581185889417065 3 0 0 True
229 tool_research_00027 tool_research evidence_collection 4673.997999999998 27499 1513 18.17514871116986 5 1 0 True
230 tool_research_00028 tool_research evidence_collection 2161.7999999999993 32414 1401 23.13633119200571 5 1 0 True
231 tool_research_00029 tool_research evidence_collection 5903.75499999999 21437 3963 5.40928589452435 5 1 0 True
232 tool_research_00030 tool_research evidence_collection 4832.2890000000025 62170 2517 24.70003972983711 9 2 0 True
233 tool_research_00031 tool_research evidence_collection 4330.880000000007 29507 2884 10.23127600554785 6 2 1 True
234 tool_research_00032 tool_research evidence_collection 1570.5789999999952 18174 849 21.406360424028268 5 1 0 True
235 tool_research_00033 tool_research evidence_collection 1797.4840000000113 34726 2226 15.600179694519317 5 1 0 True
236 tool_research_00034 tool_research evidence_collection 3040.871999999993 19123 2094 9.13228271251194 5 1 0 True
237 tool_research_00035 tool_research evidence_collection 2986.626000000001 24572 1303 18.858019953952418 5 1 0 True
238 tool_research_00036 tool_research evidence_collection 3130.6490000000053 28061 1577 17.793912492073556 3 0 0 True
239 tool_research_00037 tool_research evidence_collection 3123.7370000000055 22728 3665 6.201364256480218 5 1 0 True
240 tool_research_00038 tool_research evidence_collection 1708.3070000000048 29910 1078 27.74582560296846 5 1 0 True
241 tool_research_00039 tool_research evidence_collection 4255.195999999998 21270 1412 15.063739376770538 5 1 0 True
242 tool_research_00040 tool_research evidence_collection 2188.941 24341 4087 5.955713237093223 5 1 0 True
243 tool_research_00041 tool_research evidence_collection 2437.484999999995 4248 1853 2.2924986508364813 3 0 0 True
244 tool_research_00042 tool_research evidence_collection 2187.698999999995 8817 2395 3.681419624217119 3 0 0 True
245 tool_research_00043 tool_research evidence_collection 5124.787999999995 36771 2156 17.055194805194805 9 2 0 True
246 tool_research_00044 tool_research evidence_collection 2136.277000000007 23014 3951 5.824854467223488 5 1 0 True
247 tool_research_00045 tool_research evidence_collection 2712.2329999999974 13715 4904 2.7966965742251224 5 1 0 True
248 tool_research_00046 tool_research evidence_collection 2093.755999999999 27149 2497 10.872647176611935 3 0 0 True
249 tool_research_00047 tool_research evidence_collection 3331.8359999999957 10694 2450 4.364897959183674 3 0 0 True
250 tool_research_00048 tool_research evidence_collection 2496.739000000005 23797 420 56.65952380952381 5 1 0 True
251 tool_research_00049 tool_research evidence_collection 3162.072999999992 37174 6914 5.376627133352618 5 1 0 True
252 tool_research_00050 tool_research evidence_collection 3349.9610000000075 20453 1503 13.608117099135063 5 1 0 True
253 tool_research_00051 tool_research evidence_collection 2585.735999999997 20752 4970 4.175452716297786 5 1 0 True
254 tool_research_00052 tool_research evidence_collection 2241.700999999992 18226 1014 17.974358974358974 5 1 0 True
255 tool_research_00053 tool_research evidence_collection 1681.621000000007 20527 1964 10.451629327902241 5 1 0 True
256 tool_research_00054 tool_research evidence_collection 4616.5809999999965 14793 1020 14.50294117647059 5 1 0 True
257 tool_research_00055 tool_research evidence_collection 1986.9599999999964 36674 1499 24.46564376250834 5 1 0 True
258 tool_research_00056 tool_research evidence_collection 3329.991000000007 21611 2138 10.108044901777362 5 1 0 True
259 tool_research_00057 tool_research evidence_collection 1935.023000000001 11508 3856 2.9844398340248963 3 0 0 True
260 tool_research_00058 tool_research evidence_collection 2901.527999999999 31197 1663 18.759470835838844 5 1 0 True
261 tool_research_00059 tool_research evidence_collection 3321.638000000007 11370 816 13.933823529411764 3 0 0 True
262 tool_research_00060 tool_research evidence_collection 3683.4269999999947 22492 1908 11.78825995807128 5 1 0 True
263 tool_research_00061 tool_research evidence_collection 2848.731999999998 18988 1760 10.788636363636364 5 1 0 True
264 tool_research_00062 tool_research evidence_collection 2672.6560000000036 11461 1837 6.238976592270006 5 1 0 True
265 tool_research_00063 tool_research evidence_collection 2669.6290000000004 12186 2987 4.079678607298293 3 0 0 True
266 tool_research_00064 tool_research evidence_collection 1733.4749999999985 20624 2281 9.041648399824638 5 1 0 True
267 tool_research_00065 tool_research evidence_collection 1969.7800000000002 37289 2064 18.066375968992247 5 1 0 True
268 tool_research_00066 tool_research evidence_collection 2515.674000000004 27763 948 29.285864978902953 5 1 0 True
269 tool_research_00067 tool_research evidence_collection 3096.862999999999 25812 1096 23.55109489051095 5 1 0 True
270 tool_research_00068 tool_research evidence_collection 2049.244999999999 27451 1646 16.677399756986635 5 1 0 True
271 tool_research_00069 tool_research evidence_collection 1731.0909999999922 25997 2954 8.800609343263371 5 1 0 True
272 tool_research_00070 tool_research evidence_collection 3312.636999999995 31567 3135 10.069218500797447 5 1 0 True
273 tool_research_00071 tool_research evidence_collection 1862.328000000005 20908 2780 7.520863309352518 5 1 0 True
274 tool_research_00072 tool_research evidence_collection 3047.896000000009 54132 1025 52.81170731707317 5 1 0 True
275 tool_research_00073 tool_research evidence_collection 2561.8630000000026 21435 4790 4.474947807933194 5 1 0 True
276 tool_research_00074 tool_research evidence_collection 4560.357999999994 79773 2385 33.44779874213837 13 3 0 True
277 tool_research_00075 tool_research evidence_collection 3243.395000000007 7843 2993 2.6204477113264284 3 0 0 True
278 tool_research_00076 tool_research evidence_collection 2738.9289999999987 23031 2795 8.240071556350626 5 1 0 True
279 tool_research_00077 tool_research evidence_collection 5143.501999999998 26921 3689 7.297641637300082 3 0 0 True
280 tool_research_00078 tool_research evidence_collection 2541.331999999997 10770 5383 2.000743080066877 3 0 0 True
281 tool_research_00079 tool_research evidence_collection 4596.682000000002 30560 3128 9.769820971867007 9 2 0 True
282 tool_research_00080 tool_research evidence_collection 2516.4350000000013 10007 1693 5.910809214412286 3 0 0 True
283 tool_research_00081 tool_research evidence_collection 3084.7260000000033 17944 830 21.619277108433735 5 1 0 True
284 tool_research_00082 tool_research evidence_collection 2914.749999999998 25400 982 25.865580448065174 5 1 0 True
285 tool_research_00083 tool_research evidence_collection 2230.4889999999914 24604 2144 11.475746268656716 5 1 0 True
286 tool_research_00084 tool_research evidence_collection 3443.204000000009 24850 739 33.62652232746955 5 1 0 True
287 tool_research_00085 tool_research evidence_collection 5764.497000000006 31697 6531 4.853314959424284 6 2 1 True
288 tool_research_00086 tool_research evidence_collection 2663.731999999996 14968 967 15.478800413650465 5 1 0 True
289 tool_research_00087 tool_research evidence_collection 1660.2049999999906 10680 3250 3.286153846153846 5 1 0 True
290 tool_research_00088 tool_research evidence_collection 1999.1580000000085 11601 3306 3.5090744101633393 3 0 0 True
291 tool_research_00089 tool_research evidence_collection 2695.4450000000065 10711 3265 3.280551301684533 5 1 0 True
292 tool_research_00090 tool_research evidence_collection 5276.9389999999985 15851 1980 8.005555555555556 5 1 0 True
293 tool_research_00091 tool_research evidence_collection 5764.26699999999 27062 2151 12.581125058112505 6 2 1 True
294 tool_research_00092 tool_research evidence_collection 1482.0979999999936 17916 936 19.141025641025642 5 1 0 True
295 tool_research_00093 tool_research evidence_collection 2160.2140000000104 36749 2052 17.908869395711502 5 1 0 True
296 tool_research_00094 tool_research evidence_collection 3420.692000000017 15674 8252 1.8994183228308288 3 0 0 True
297 tool_research_00095 tool_research evidence_collection 1882.05099999999 19776 2123 9.315120113047573 5 1 0 True
298 tool_research_00096 tool_research evidence_collection 3586.549000000005 36710 1309 28.044308632543927 5 1 0 True
299 tool_research_00097 tool_research evidence_collection 1987.364999999997 14435 3124 4.62067861715749 5 1 0 True
300 tool_research_00098 tool_research evidence_collection 3917.211000000009 16232 1378 11.779390420899855 6 2 1 True
301 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
1 timeout_probability max_retries success_rate mean_retries mean_amplification mean_latency_ms
2 0.0 0 1.0 0.0 9.014727352307537 1829.8204232372348
3 0.0 1 1.0 0.0 9.017931822157774 1786.1398565415025
4 0.0 2 1.0 0.0 9.497944538818517 1655.013246029438
5 0.0 3 1.0 0.0 8.981130309004985 1716.8465797602803
6 0.0 5 1.0 0.0 9.540066677486474 1716.7430554392593
7 0.03 0 0.9666666666666667 0.0 9.063950194066456 1669.7925665017842
8 0.03 1 0.9958333333333333 0.016666666666666666 9.063781276545864 1657.0420076151597
9 0.03 2 1.0 0.016666666666666666 9.014566351856745 1691.3863870856096
10 0.03 3 1.0 0.020833333333333332 9.637237082920953 1721.830506046892
11 0.03 5 1.0 0.0125 9.649347558637414 1718.5997383083138
12 0.08 0 0.9041666666666667 0.0 8.25627307377185 1635.0229558657152
13 0.08 1 1.0 0.05416666666666667 9.289215941037927 1787.9821751080794
14 0.08 2 1.0 0.06666666666666667 9.431797013914702 1916.4375526605215
15 0.08 3 1.0 0.058333333333333334 9.050271941109205 1898.8272546658047
16 0.08 5 1.0 0.07916666666666666 9.741006123762736 1970.2545335768014
17 0.15 0 0.8416666666666667 0.0 8.164931539209656 1610.0725491672833
18 0.15 1 0.9833333333333333 0.10833333333333334 9.088215821284614 1938.8382504596384
19 0.15 2 1.0 0.1 9.261076832398844 1941.657277871303
20 0.15 3 0.9958333333333333 0.13333333333333333 11.372866350773522 2027.2488180006546
21 0.15 5 1.0 0.13333333333333333 8.152159646681561 2064.0974036821353
22 0.25 0 0.7916666666666666 0.0 7.82021056651408 1652.063945123461
23 0.25 1 0.9541666666666667 0.17916666666666667 8.424662742312817 2194.736913880946
24 0.25 2 0.9916666666666667 0.2875 9.275168718803195 2475.475754982108
25 0.25 3 1.0 0.2833333333333333 8.808713566195896 2429.5919980366966
26 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
1 arrival_rate offered_tasks completed_tasks throughput_per_second mean_delay_ms p95_delay_ms queue_peak drop_rate success_rate mean_amplification
2 0.5 87 79 0.49375 5690.601711699437 12756.456777674 2 0.0 1.0 32.68982726898488
3 1.0 178 154 0.9625 28654.713037581158 50223.56851458479 35 0.0 1.0 35.61819225706701
4 2.0 354 315 1.96875 159265.0479860076 259462.94208402873 216 0.0 1.0 27.685762197623816
5 4.0 735 553 3.45625 360462.8938916123 611043.0735286651 500 0.1251700680272109 0.9981916817359855 28.819579849617657
6 6.0 1140 538 3.3625 406978.074020204 627164.1820327837 500 0.4280701754385965 1.0 30.664346517813648
7 8.0 1419 478 2.9875 439078.312694735 605565.2288237411 500 0.5419309372797745 0.997907949790795 28.477068296105013
8 10.0 1736 459 2.86875 462378.903316947 623226.2655493785 500 0.6215437788018433 0.9978213507625272 29.655131218317656
9 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
1 model metric mae rmse mape_percent
2 full_model internal_bytes 9852.85421644164 11957.784318614104 27.25831155178904
3 full_model latency_ms 1677.2186263904505 2068.228406399321 38.01609858429338
4 full_model message_count 0.43277777777777793 0.5471686380984558 5.855207621776822
5 full_model tool_calls 0.11166666666666662 0.14041275134666625 14.427527090058401
6 full_model amplification 4.305062499013978 5.243570352907988 22.67666226433828
7 no_context internal_bytes 28387.670805477606 38228.5095522755 119.54177279524332
8 no_context latency_ms 2907.231795727213 3869.904048337353 62.66674153347929
9 no_context message_count 2.485555555555556 3.1931712438565825 38.768826743972944
10 no_context tool_calls 0.6505555555555556 0.7056603159321639 196.9584307828373
11 no_context amplification 10.922275115304535 13.789521598016519 70.65863904754978
12 static_mean internal_bytes 29834.93333333333 32709.783175317236 230.39064998346973
13 static_mean latency_ms 2757.6886622222223 3058.6901465213614 119.58343818448623
14 static_mean message_count 2.5155555555555558 2.7855500155066126 48.03496553983882
15 static_mean tool_calls 0.5444444444444444 0.6355225321645873 264.95059144468667
16 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
1 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
2 collaborative_analysis static_mean 82782.45 38030.049999999996 8428.771760000001 4292.238766666668 9.88 6.1066666666666665 1.66 0.9266666666666667 33.798140646040636 17.719989109017618
3 collaborative_analysis no_context 82782.45 18429.737056529975 8428.771760000001 1933.7549094389146 9.88 4.658333333333333 1.66 0.6333333333333333 33.798140646040636 10.99100144733211
4 collaborative_analysis full_model 82782.45 65408.811967296744 8428.771760000001 5132.429177599434 9.88 9.033333333333333 1.66 1.4333333333333333 33.798140646040636 25.68477275651994
5 simple_qa static_mean 5514.23 38030.049999999996 1128.43623 4292.238766666668 3.24 6.1066666666666665 0.11 0.9266666666666667 4.875984197964249 17.719989109017618
6 simple_qa no_context 5514.23 19556.05971301258 1128.43623 1878.3339705388123 3.24 5.0 0.11 0.65 4.875984197964249 10.442958092513376
7 simple_qa full_model 5514.23 4564.059252059445 1128.43623 740.9752102854878 3.24 3.2666666666666666 0.11 0.13333333333333333 4.875984197964249 4.07657616682107
8 tool_research static_mean 25793.47 38030.049999999996 3319.5083100000024 4292.238766666668 5.2 6.1066666666666665 1.01 0.9266666666666667 14.485842483047964 17.719989109017618
9 tool_research no_context 25793.47 19025.000240049787 3319.5083100000024 1842.727513918263 5.2 4.725 1.01 0.625 14.485842483047964 10.09313023039201
10 tool_research full_model 25793.47 14558.716131318892 3319.5083100000024 1971.65603294373 5.2 4.775 1.01 0.925 14.485842483047964 10.483430906669906