{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CYEOZUV6IRY6GPLCXXWASZJRPI","short_pith_number":"pith:CYEOZUV6","schema_version":"1.0","canonical_sha256":"1608ecd2be4471e33d62bdec0965317a171f433d4140e9a5714b7d35868fffff","source":{"kind":"arxiv","id":"2501.14225","version":2},"attestation_state":"computed","paper":{"title":"Multi-agent KTO: Reinforcing Strategic Interactions of Large Language Model in Language Game","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.CL","authors_text":"Haoyu Kuang, Peng Sun, Rong Ye, Yikai Zhang, Yongxin Zhang, Zhongyu Wei","submitted_at":"2025-01-24T04:09:03Z","abstract_excerpt":"Achieving Artificial General Intelligence (AGI) requires AI agents that can not only make stratigic decisions but also engage in flexible and meaningful communication. Inspired by Wittgenstein's language game theory in Philosophical Investigations, we propose that language agents can learn through in-context interaction rather than traditional multi-stage frameworks that separate decision-making from language expression. Using Werewolf, a social deduction game that tests language understanding, strategic interaction, and adaptability, we develop the Multi-agent Kahneman & Tversky's Optimizatio"},"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":"2501.14225","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-24T04:09:03Z","cross_cats_sorted":["cs.AI","cs.HC"],"title_canon_sha256":"28d2a2dae11fa9d7195426e6ba8f37ea24d9f7959b911c31676d07975561d1b5","abstract_canon_sha256":"3cbd0e8b917066479b6c15224968538fb72b3f87e9f3b52786bac2ef896ee387"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:30:30.422925Z","signature_b64":"uVpBOl5lQT9Pl3KGAMgssy1hDRfdZthHLNRGEg44R0eTesD+R6J3CbHXFDMDjtjGI3HNhLPZz5/IG+lFCLviAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1608ecd2be4471e33d62bdec0965317a171f433d4140e9a5714b7d35868fffff","last_reissued_at":"2026-07-05T10:30:30.422405Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:30:30.422405Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-agent KTO: Reinforcing Strategic Interactions of Large Language Model in Language Game","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.CL","authors_text":"Haoyu Kuang, Peng Sun, Rong Ye, Yikai Zhang, Yongxin Zhang, Zhongyu Wei","submitted_at":"2025-01-24T04:09:03Z","abstract_excerpt":"Achieving Artificial General Intelligence (AGI) requires AI agents that can not only make stratigic decisions but also engage in flexible and meaningful communication. Inspired by Wittgenstein's language game theory in Philosophical Investigations, we propose that language agents can learn through in-context interaction rather than traditional multi-stage frameworks that separate decision-making from language expression. Using Werewolf, a social deduction game that tests language understanding, strategic interaction, and adaptability, we develop the Multi-agent Kahneman & Tversky's Optimizatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.14225","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/2501.14225/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":"2501.14225","created_at":"2026-07-05T10:30:30.422469+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.14225v2","created_at":"2026-07-05T10:30:30.422469+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.14225","created_at":"2026-07-05T10:30:30.422469+00:00"},{"alias_kind":"pith_short_12","alias_value":"CYEOZUV6IRY6","created_at":"2026-07-05T10:30:30.422469+00:00"},{"alias_kind":"pith_short_16","alias_value":"CYEOZUV6IRY6GPLC","created_at":"2026-07-05T10:30:30.422469+00:00"},{"alias_kind":"pith_short_8","alias_value":"CYEOZUV6","created_at":"2026-07-05T10:30:30.422469+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.14892","citing_title":"Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systems","ref_index":290,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14892","citing_title":"Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systems","ref_index":289,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CYEOZUV6IRY6GPLCXXWASZJRPI","json":"https://pith.science/pith/CYEOZUV6IRY6GPLCXXWASZJRPI.json","graph_json":"https://pith.science/api/pith-number/CYEOZUV6IRY6GPLCXXWASZJRPI/graph.json","events_json":"https://pith.science/api/pith-number/CYEOZUV6IRY6GPLCXXWASZJRPI/events.json","paper":"https://pith.science/paper/CYEOZUV6"},"agent_actions":{"view_html":"https://pith.science/pith/CYEOZUV6IRY6GPLCXXWASZJRPI","download_json":"https://pith.science/pith/CYEOZUV6IRY6GPLCXXWASZJRPI.json","view_paper":"https://pith.science/paper/CYEOZUV6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.14225&json=true","fetch_graph":"https://pith.science/api/pith-number/CYEOZUV6IRY6GPLCXXWASZJRPI/graph.json","fetch_events":"https://pith.science/api/pith-number/CYEOZUV6IRY6GPLCXXWASZJRPI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CYEOZUV6IRY6GPLCXXWASZJRPI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CYEOZUV6IRY6GPLCXXWASZJRPI/action/storage_attestation","attest_author":"https://pith.science/pith/CYEOZUV6IRY6GPLCXXWASZJRPI/action/author_attestation","sign_citation":"https://pith.science/pith/CYEOZUV6IRY6GPLCXXWASZJRPI/action/citation_signature","submit_replication":"https://pith.science/pith/CYEOZUV6IRY6GPLCXXWASZJRPI/action/replication_record"}},"created_at":"2026-07-05T10:30:30.422469+00:00","updated_at":"2026-07-05T10:30:30.422469+00:00"}