{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:N4MJN3COUM4G7OVFI5IF76EXQP","short_pith_number":"pith:N4MJN3CO","schema_version":"1.0","canonical_sha256":"6f1896ec4ea3386fbaa547505ff89783fc20e839c27a37ad273fe9823413acbe","source":{"kind":"arxiv","id":"2502.16565","version":2},"attestation_state":"computed","paper":{"title":"The Hidden Strength of Disagreement: Unraveling the Consensus-Diversity Tradeoff in Adaptive Multi-Agent Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CY"],"primary_cat":"cs.MA","authors_text":"Takayuki Ito, Zengqing Wu","submitted_at":"2025-02-23T13:12:53Z","abstract_excerpt":"Consensus formation is pivotal in multi-agent systems (MAS), balancing collective coherence with individual diversity. Conventional LLM-based MAS primarily rely on explicit coordination, e.g., prompts or voting, risking premature homogenization. We argue that implicit consensus, where agents exchange information yet independently form decisions via in-context learning, can be more effective in dynamic environments that require long-horizon adaptability. By retaining partial diversity, systems can better explore novel strategies and cope with external shocks. We formalize a consensus-diversity "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2502.16565","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2025-02-23T13:12:53Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CY"],"title_canon_sha256":"fdb6dcc04ecaa52687b6ba7ed1cb50c8f9720c11a728fe52bb5984c0d811d0b3","abstract_canon_sha256":"299bf7f2eef22a4d3c91dbf2ae1c20461f5ebf70da2b1455a6ee0ac0af0824db"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:23.524760Z","signature_b64":"POnXgEYc7T7RpCJd9Ftrif9+wGk22MMefkbK3wbOFrRnvkdIRZ6k+JTCfuGdYtyckxcImBHQiMn2Jncf/s++AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6f1896ec4ea3386fbaa547505ff89783fc20e839c27a37ad273fe9823413acbe","last_reissued_at":"2026-07-05T11:05:23.524267Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:23.524267Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Hidden Strength of Disagreement: Unraveling the Consensus-Diversity Tradeoff in Adaptive Multi-Agent Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CY"],"primary_cat":"cs.MA","authors_text":"Takayuki Ito, Zengqing Wu","submitted_at":"2025-02-23T13:12:53Z","abstract_excerpt":"Consensus formation is pivotal in multi-agent systems (MAS), balancing collective coherence with individual diversity. Conventional LLM-based MAS primarily rely on explicit coordination, e.g., prompts or voting, risking premature homogenization. We argue that implicit consensus, where agents exchange information yet independently form decisions via in-context learning, can be more effective in dynamic environments that require long-horizon adaptability. By retaining partial diversity, systems can better explore novel strategies and cope with external shocks. We formalize a consensus-diversity "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.16565","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2502.16565/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2502.16565","created_at":"2026-07-05T11:05:23.524326+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.16565v2","created_at":"2026-07-05T11:05:23.524326+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.16565","created_at":"2026-07-05T11:05:23.524326+00:00"},{"alias_kind":"pith_short_12","alias_value":"N4MJN3COUM4G","created_at":"2026-07-05T11:05:23.524326+00:00"},{"alias_kind":"pith_short_16","alias_value":"N4MJN3COUM4G7OVF","created_at":"2026-07-05T11:05:23.524326+00:00"},{"alias_kind":"pith_short_8","alias_value":"N4MJN3CO","created_at":"2026-07-05T11:05:23.524326+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.21588","citing_title":"Herd Behavior: Investigating Peer Influence in LLM-based Multi-Agent Systems","ref_index":33,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N4MJN3COUM4G7OVFI5IF76EXQP","json":"https://pith.science/pith/N4MJN3COUM4G7OVFI5IF76EXQP.json","graph_json":"https://pith.science/api/pith-number/N4MJN3COUM4G7OVFI5IF76EXQP/graph.json","events_json":"https://pith.science/api/pith-number/N4MJN3COUM4G7OVFI5IF76EXQP/events.json","paper":"https://pith.science/paper/N4MJN3CO"},"agent_actions":{"view_html":"https://pith.science/pith/N4MJN3COUM4G7OVFI5IF76EXQP","download_json":"https://pith.science/pith/N4MJN3COUM4G7OVFI5IF76EXQP.json","view_paper":"https://pith.science/paper/N4MJN3CO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.16565&json=true","fetch_graph":"https://pith.science/api/pith-number/N4MJN3COUM4G7OVFI5IF76EXQP/graph.json","fetch_events":"https://pith.science/api/pith-number/N4MJN3COUM4G7OVFI5IF76EXQP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N4MJN3COUM4G7OVFI5IF76EXQP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N4MJN3COUM4G7OVFI5IF76EXQP/action/storage_attestation","attest_author":"https://pith.science/pith/N4MJN3COUM4G7OVFI5IF76EXQP/action/author_attestation","sign_citation":"https://pith.science/pith/N4MJN3COUM4G7OVFI5IF76EXQP/action/citation_signature","submit_replication":"https://pith.science/pith/N4MJN3COUM4G7OVFI5IF76EXQP/action/replication_record"}},"created_at":"2026-07-05T11:05:23.524326+00:00","updated_at":"2026-07-05T11:05:23.524326+00:00"}