{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WVS6S47CNJXFQNY26RJFXYPMEJ","short_pith_number":"pith:WVS6S47C","schema_version":"1.0","canonical_sha256":"b565e973e26a6e58371af4525be1ec2269155bf7629845d3090418408c568910","source":{"kind":"arxiv","id":"2508.02076","version":1},"attestation_state":"computed","paper":{"title":"Everyone Contributes! Incentivizing Strategic Cooperation in Multi-LLM Systems via Sequential Public Goods Games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT"],"primary_cat":"cs.AI","authors_text":"Jingyuan Yang, Shaochong Lin, Yuan Qu, Yunhao Liang, Zuo-Jun Max Shen","submitted_at":"2025-08-04T05:36:07Z","abstract_excerpt":"Coordinating multiple large language models (LLMs) to solve complex tasks collaboratively poses a fundamental trade-off between the computation costs and collective performance compared with individual model. We introduce a novel, game-theoretically grounded reinforcement learning (RL) framework, the Multi-Agent Cooperation Sequential Public Goods Game (MAC-SPGG), to systematically incentivize cooperation in multi-LLM ensembles. In MAC-SPGG, LLM agents move in sequence, observing predecessors' outputs and updating beliefs to condition their own contributions. By redesigning the public-goods re"},"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":"2508.02076","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-08-04T05:36:07Z","cross_cats_sorted":["cs.GT"],"title_canon_sha256":"6559a977d7c5b0a78dc4e0e46313f4a7e34d1994205a62183c0c2a3b678bd071","abstract_canon_sha256":"6896d81989ce9661e4567b6d4468b691e567479b64ef0d4f06f4c2bb3dd936b2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:47:50.459465Z","signature_b64":"L54ZJWaGkXif0fwzKlcZoChIp+6vFzc2SWSkWNAv8h3BXL31VeJjd3NvdoUeBxsbXRaKfpPDaGkpGBlsAQC3Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b565e973e26a6e58371af4525be1ec2269155bf7629845d3090418408c568910","last_reissued_at":"2026-07-05T11:47:50.459056Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:47:50.459056Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Everyone Contributes! Incentivizing Strategic Cooperation in Multi-LLM Systems via Sequential Public Goods Games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT"],"primary_cat":"cs.AI","authors_text":"Jingyuan Yang, Shaochong Lin, Yuan Qu, Yunhao Liang, Zuo-Jun Max Shen","submitted_at":"2025-08-04T05:36:07Z","abstract_excerpt":"Coordinating multiple large language models (LLMs) to solve complex tasks collaboratively poses a fundamental trade-off between the computation costs and collective performance compared with individual model. We introduce a novel, game-theoretically grounded reinforcement learning (RL) framework, the Multi-Agent Cooperation Sequential Public Goods Game (MAC-SPGG), to systematically incentivize cooperation in multi-LLM ensembles. In MAC-SPGG, LLM agents move in sequence, observing predecessors' outputs and updating beliefs to condition their own contributions. By redesigning the public-goods re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.02076","kind":"arxiv","version":1},"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/2508.02076/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":"2508.02076","created_at":"2026-07-05T11:47:50.459108+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.02076v1","created_at":"2026-07-05T11:47:50.459108+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.02076","created_at":"2026-07-05T11:47:50.459108+00:00"},{"alias_kind":"pith_short_12","alias_value":"WVS6S47CNJXF","created_at":"2026-07-05T11:47:50.459108+00:00"},{"alias_kind":"pith_short_16","alias_value":"WVS6S47CNJXFQNY2","created_at":"2026-07-05T11:47:50.459108+00:00"},{"alias_kind":"pith_short_8","alias_value":"WVS6S47C","created_at":"2026-07-05T11:47:50.459108+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.15236","citing_title":"Agentic Microphysics: A Manifesto for Generative AI Safety","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WVS6S47CNJXFQNY26RJFXYPMEJ","json":"https://pith.science/pith/WVS6S47CNJXFQNY26RJFXYPMEJ.json","graph_json":"https://pith.science/api/pith-number/WVS6S47CNJXFQNY26RJFXYPMEJ/graph.json","events_json":"https://pith.science/api/pith-number/WVS6S47CNJXFQNY26RJFXYPMEJ/events.json","paper":"https://pith.science/paper/WVS6S47C"},"agent_actions":{"view_html":"https://pith.science/pith/WVS6S47CNJXFQNY26RJFXYPMEJ","download_json":"https://pith.science/pith/WVS6S47CNJXFQNY26RJFXYPMEJ.json","view_paper":"https://pith.science/paper/WVS6S47C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.02076&json=true","fetch_graph":"https://pith.science/api/pith-number/WVS6S47CNJXFQNY26RJFXYPMEJ/graph.json","fetch_events":"https://pith.science/api/pith-number/WVS6S47CNJXFQNY26RJFXYPMEJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WVS6S47CNJXFQNY26RJFXYPMEJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WVS6S47CNJXFQNY26RJFXYPMEJ/action/storage_attestation","attest_author":"https://pith.science/pith/WVS6S47CNJXFQNY26RJFXYPMEJ/action/author_attestation","sign_citation":"https://pith.science/pith/WVS6S47CNJXFQNY26RJFXYPMEJ/action/citation_signature","submit_replication":"https://pith.science/pith/WVS6S47CNJXFQNY26RJFXYPMEJ/action/replication_record"}},"created_at":"2026-07-05T11:47:50.459108+00:00","updated_at":"2026-07-05T11:47:50.459108+00:00"}