{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GU5BIEPCSCLA2HF4YSO5D2IKV5","short_pith_number":"pith:GU5BIEPC","schema_version":"1.0","canonical_sha256":"353a1411e290960d1cbcc49dd1e90aaf59e0e9194eea145052884ad12a953811","source":{"kind":"arxiv","id":"2310.03903","version":3},"attestation_state":"computed","paper":{"title":"LLM-Coordination: Evaluating and Analyzing Multi-agent Coordination Abilities in Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.CL","authors_text":"Anthony Reyna, Saaket Agashe, Xin Eric Wang, Yue Fan","submitted_at":"2023-10-05T21:18:15Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated emergent common-sense reasoning and Theory of Mind (ToM) capabilities, making them promising candidates for developing coordination agents. This study introduces the LLM-Coordination Benchmark, a novel benchmark for analyzing LLMs in the context of Pure Coordination Settings, where agents must cooperate to maximize gains. Our benchmark evaluates LLMs through two distinct tasks. The first is Agentic Coordination, where LLMs act as proactive participants in four pure coordination games. The second is Coordination Question Answering (CoordQA), which "},"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":"2310.03903","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-05T21:18:15Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"0a72415453ed888c5ed9fab45fff08c6d78873e3070309138a55fe72392c0566","abstract_canon_sha256":"c500a1414b96909c6b014a0d3784b873559f9d66258a9e31b0b9b1088a553fb0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:55:17.049171Z","signature_b64":"h7tfYQcw5CM49g7usKiSIhAYTSl+8Hk+Lo2sueSPTG41R89Cu/N5ZqjZAHeoDexhTg4gTdp6C8RuFKV/AqvTBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"353a1411e290960d1cbcc49dd1e90aaf59e0e9194eea145052884ad12a953811","last_reissued_at":"2026-07-05T10:55:17.048684Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:55:17.048684Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLM-Coordination: Evaluating and Analyzing Multi-agent Coordination Abilities in Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.CL","authors_text":"Anthony Reyna, Saaket Agashe, Xin Eric Wang, Yue Fan","submitted_at":"2023-10-05T21:18:15Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated emergent common-sense reasoning and Theory of Mind (ToM) capabilities, making them promising candidates for developing coordination agents. This study introduces the LLM-Coordination Benchmark, a novel benchmark for analyzing LLMs in the context of Pure Coordination Settings, where agents must cooperate to maximize gains. Our benchmark evaluates LLMs through two distinct tasks. The first is Agentic Coordination, where LLMs act as proactive participants in four pure coordination games. The second is Coordination Question Answering (CoordQA), which "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.03903","kind":"arxiv","version":3},"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/2310.03903/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":"2310.03903","created_at":"2026-07-05T10:55:17.048738+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.03903v3","created_at":"2026-07-05T10:55:17.048738+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.03903","created_at":"2026-07-05T10:55:17.048738+00:00"},{"alias_kind":"pith_short_12","alias_value":"GU5BIEPCSCLA","created_at":"2026-07-05T10:55:17.048738+00:00"},{"alias_kind":"pith_short_16","alias_value":"GU5BIEPCSCLA2HF4","created_at":"2026-07-05T10:55:17.048738+00:00"},{"alias_kind":"pith_short_8","alias_value":"GU5BIEPC","created_at":"2026-07-05T10:55:17.048738+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07021","citing_title":"Learning social norms enhances compatibility in dynamic human-AI coordination","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2606.09931","citing_title":"A Note on the Strategic Confinement Problem","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2506.02387","citing_title":"VS-Bench: Evaluating VLMs for Strategic Abilities in Multi-Agent Environments","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2601.10102","citing_title":"When Identity Overrides Incentives: Representational Choices as Governance Decisions in Multi-Agent LLM Systems","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2511.20857","citing_title":"Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory","ref_index":97,"is_internal_anchor":false},{"citing_arxiv_id":"2503.13657","citing_title":"Why Do Multi-Agent LLM Systems Fail?","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03310","citing_title":"Coordination as an Architectural Layer for LLM-Based Multi-Agent Systems","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GU5BIEPCSCLA2HF4YSO5D2IKV5","json":"https://pith.science/pith/GU5BIEPCSCLA2HF4YSO5D2IKV5.json","graph_json":"https://pith.science/api/pith-number/GU5BIEPCSCLA2HF4YSO5D2IKV5/graph.json","events_json":"https://pith.science/api/pith-number/GU5BIEPCSCLA2HF4YSO5D2IKV5/events.json","paper":"https://pith.science/paper/GU5BIEPC"},"agent_actions":{"view_html":"https://pith.science/pith/GU5BIEPCSCLA2HF4YSO5D2IKV5","download_json":"https://pith.science/pith/GU5BIEPCSCLA2HF4YSO5D2IKV5.json","view_paper":"https://pith.science/paper/GU5BIEPC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.03903&json=true","fetch_graph":"https://pith.science/api/pith-number/GU5BIEPCSCLA2HF4YSO5D2IKV5/graph.json","fetch_events":"https://pith.science/api/pith-number/GU5BIEPCSCLA2HF4YSO5D2IKV5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GU5BIEPCSCLA2HF4YSO5D2IKV5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GU5BIEPCSCLA2HF4YSO5D2IKV5/action/storage_attestation","attest_author":"https://pith.science/pith/GU5BIEPCSCLA2HF4YSO5D2IKV5/action/author_attestation","sign_citation":"https://pith.science/pith/GU5BIEPCSCLA2HF4YSO5D2IKV5/action/citation_signature","submit_replication":"https://pith.science/pith/GU5BIEPCSCLA2HF4YSO5D2IKV5/action/replication_record"}},"created_at":"2026-07-05T10:55:17.048738+00:00","updated_at":"2026-07-05T10:55:17.048738+00:00"}