repro-evomas / logbook.json
ParetoOptimal's picture
Update logbook: Repro - Evolutionary Generation of Multi-Agent Systems
c6eb824 verified
Raw
History Blame Contribute Delete
2.37 kB
{
"schema_version": 1,
"title": "Repro - Evolutionary Generation of Multi-Agent Systems",
"emoji": "🎯",
"space_id": "ParetoOptimal/repro-evomas",
"paper": {
"arxiv_id": "2602.06511"
},
"tags": [
"icml2026-repro",
"paper-ic0AGRIkmY"
],
"updated_at": "2026-07-16T23:50:55+00:00",
"root": {
"slug": "index",
"title": "Repro - Evolutionary Generation of Multi-Agent Systems",
"file": "pages/index.md",
"children": [
{
"slug": "paper-approach",
"title": "Paper & approach",
"file": "pages/paper-approach/page.md",
"children": []
},
{
"slug": "claim-2-bbeh-accuracy-vs-baselines-toy",
"title": "Official claim 1: +10.5 over EvoAgent on BBEH, +7.1 on WorkBench (toy-scale direction test)",
"file": "pages/claim-2-bbeh-accuracy-vs-baselines-toy/page.md",
"children": []
},
{
"slug": "claim-3-swe-bench-verified-79-1-audit-only",
"title": "Official claim 2: 79.1% on SWE-Bench-Verified with Claude-4.5-Sonnet (audit only)",
"file": "pages/claim-3-swe-bench-verified-79-1-audit-only/page.md",
"children": []
},
{
"slug": "claim-5-execution-rate",
"title": "Official claim 3: higher executability and runtime robustness (execution-rate measurements)",
"file": "pages/claim-5-execution-rate/page.md",
"children": []
},
{
"slug": "claim-1-structured-configuration-generation",
"title": "Evidence A: the EvoMAS mechanism — structured configs + evolutionary loop (underpins official claims 1 and 3)",
"file": "pages/claim-1-structured-configuration-generation/page.md",
"children": []
},
{
"slug": "claim-4-meta-model-sensitivity-toy",
"title": "Evidence B: meta-model sensitivity (supports official claims 1 and 3)",
"file": "pages/claim-4-meta-model-sensitivity-toy/page.md",
"children": []
},
{
"slug": "evomas-repro",
"title": "evomas-repro",
"file": "pages/evomas-repro/page.md",
"children": []
},
{
"slug": "conclusion",
"title": "Conclusion",
"file": "pages/conclusion/page.md",
"children": []
}
]
},
"agent_view_tokens": 11860,
"revision": "1784245855730112194"
}