{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:IO25R27PGJ2BRQSC2ZRSCVUKWQ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"f97f50f3f927448c1b51e7003903b992e1b7e2ad965df5ac2b5b0bc6d19ed775","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2026-02-04T05:53:21Z","title_canon_sha256":"16270a1613a3cd5d62be162b2353fd1c34973ee1464ce826db02fa5faaa802f4"},"schema_version":"1.0","source":{"id":"2602.04234","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.04234","created_at":"2026-06-05T01:15:19Z"},{"alias_kind":"arxiv_version","alias_value":"2602.04234v6","created_at":"2026-06-05T01:15:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.04234","created_at":"2026-06-05T01:15:19Z"},{"alias_kind":"pith_short_12","alias_value":"IO25R27PGJ2B","created_at":"2026-06-05T01:15:19Z"},{"alias_kind":"pith_short_16","alias_value":"IO25R27PGJ2BRQSC","created_at":"2026-06-05T01:15:19Z"},{"alias_kind":"pith_short_8","alias_value":"IO25R27P","created_at":"2026-06-05T01:15:19Z"}],"graph_snapshots":[{"event_id":"sha256:be61195e5cf2455fdab8fa0891d279a42cbd366513dce6fff929655241579098","target":"graph","created_at":"2026-06-05T01:15:19Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"a single agent outperforms MAS in approximately 43.3% of cases, and that entropy dynamics are largely determined during the first round of interaction... we introduce a simple yet effective algorithm, the Entropy Judger, to select solutions from MAS's pass@k results, leading to consistent accuracy improvements across all MAS configurations and tasks."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the 245 entropy features extracted at token, agent, and round levels are sufficient to capture the causal drivers of MAS success or failure without significant confounding from model-specific tokenization or prompt formatting choices."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Entropy patterns show single LLMs often outperform multi-agent groups, first-round dynamics dominate, and an entropy judger improves solution selection across benchmarks."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Single-agent setups outperform multi-agent LLM collaboration in 43 percent of cases because entropy patterns stabilize after the first round."}],"snapshot_sha256":"949af1ec48e71d33a7e3a6167c3c2b36ba2860f6827b6757ee04352035e3455b"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2602.04234/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-agent systems (MAS) have emerged as a prominent paradigm for leveraging large language models (LLMs) to tackle complex tasks. However, the mechanisms governing the effectiveness of MAS built upon publicly available LLMs, specifically the underlying rationales for their success or failure, remain largely unexplored. In this paper, we revisit MAS through the perspective of \\textit{entropy}, considering both intra- and inter-agent dynamics by investigating entropy transitions during problem-solving across various topologies, six reasoning benchmarks, and two agentic tasks. By analyzing 245 ","authors_text":"Ningxin Su, Sijia Chen, Yuxuan Zhao","cross_cats":[],"headline":"Single-agent setups outperform multi-agent LLM collaboration in 43 percent of cases because entropy patterns stabilize after the first round.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2026-02-04T05:53:21Z","title":"When Does Multi-Agent Collaboration Help? An Entropy Perspective"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.04234","kind":"arxiv","version":6},"verdict":{"created_at":"2026-05-16T07:34:07.186419Z","id":"e7f97df1-76e8-474a-b6c0-3723489a0539","model_set":{"reader":"grok-4.3"},"one_line_summary":"Entropy patterns show single LLMs often outperform multi-agent groups, first-round dynamics dominate, and an entropy judger improves solution selection across benchmarks.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Single-agent setups outperform multi-agent LLM collaboration in 43 percent of cases because entropy patterns stabilize after the first round.","strongest_claim":"a single agent outperforms MAS in approximately 43.3% of cases, and that entropy dynamics are largely determined during the first round of interaction... we introduce a simple yet effective algorithm, the Entropy Judger, to select solutions from MAS's pass@k results, leading to consistent accuracy improvements across all MAS configurations and tasks.","weakest_assumption":"That the 245 entropy features extracted at token, agent, and round levels are sufficient to capture the causal drivers of MAS success or failure without significant confounding from model-specific tokenization or prompt formatting choices."}},"verdict_id":"e7f97df1-76e8-474a-b6c0-3723489a0539"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8186f632e7a74d554bd3d25881d4d6ff52946117b340f791c8ce8f1821eba14f","target":"record","created_at":"2026-06-05T01:15:19Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"f97f50f3f927448c1b51e7003903b992e1b7e2ad965df5ac2b5b0bc6d19ed775","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2026-02-04T05:53:21Z","title_canon_sha256":"16270a1613a3cd5d62be162b2353fd1c34973ee1464ce826db02fa5faaa802f4"},"schema_version":"1.0","source":{"id":"2602.04234","kind":"arxiv","version":6}},"canonical_sha256":"43b5d8ebef327418c242d66321568ab4030d112c0905bcaa1d9c6dee400ebc23","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"43b5d8ebef327418c242d66321568ab4030d112c0905bcaa1d9c6dee400ebc23","first_computed_at":"2026-06-05T01:15:19.704519Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-05T01:15:19.704519Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PHueLVCVaMnVElV9G4KKM1JU3KJwctD5DlvO6B/qbT945o6PVb229RfPyPdHSMwY0UoiOM5OWB1gaVKugxfYDg==","signature_status":"signed_v1","signed_at":"2026-06-05T01:15:19.705114Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.04234","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8186f632e7a74d554bd3d25881d4d6ff52946117b340f791c8ce8f1821eba14f","sha256:be61195e5cf2455fdab8fa0891d279a42cbd366513dce6fff929655241579098"],"state_sha256":"a5196abc7dad749b84112b978c470fdc799461c1c0271d5cc19bb950586a4853"}