{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:3RCJZ5ZKJYWIVHXJDRAH6SA2XM","short_pith_number":"pith:3RCJZ5ZK","schema_version":"1.0","canonical_sha256":"dc449cf72a4e2c8a9ee91c407f481abb36f918b2c16267b105322c89e6a60d55","source":{"kind":"arxiv","id":"2605.04906","version":2},"attestation_state":"computed","paper":{"title":"Strat-Reasoner: Reinforcing Strategic Reasoning of LLMs in Multi-Agent Games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Strat-Reasoner improves LLM performance in multi-agent games by 22.1 percent through recursive modeling of other agents' reasoning and group-relative reinforcement learning.","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jiarui Gan, Jiexin Wang, Mengchen Zhao, Pengxu Yang, Yi Cai, Yidong He, Yutao Lai","submitted_at":"2026-05-06T13:35:14Z","abstract_excerpt":"While Large Language Models (LLMs) excel in certain reasoning tasks, they struggle in multi-agent games where the final outcome depends on the joint strategies of all agents. In multi-agent games, the non-stationarity of other agents brings significant challenges on the evaluation of the reasoning process and the credit assignment over multiple reasoning steps. Existing single-agent reinforcement learning (RL) approaches and their multi-agent extensions fail to address these challenges as they do not incorporate other agents in the reasoning process. In this work, we propose Strat-Reasoner, a "},"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":true},"canonical_record":{"source":{"id":"2605.04906","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-06T13:35:14Z","cross_cats_sorted":[],"title_canon_sha256":"5099b995350a9d628d4c1d02b5beb97eae7363ad3d2470883cf01cd75ac79321","abstract_canon_sha256":"6682c5ba6ba04186213d5e48b22c9dd04edd20d962feaeb17b7ae76ee46e8c40"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T02:04:12.139200Z","signature_b64":"IwEGkSZ0UlTK1BhrFhJlJMtui8nTD/IauppLyn2XAon8E4Gqz+MPhdFwkXaCrCkwZeSuntTP9f9367cPTgsRCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc449cf72a4e2c8a9ee91c407f481abb36f918b2c16267b105322c89e6a60d55","last_reissued_at":"2026-05-26T02:04:12.138521Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T02:04:12.138521Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Strat-Reasoner: Reinforcing Strategic Reasoning of LLMs in Multi-Agent Games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Strat-Reasoner improves LLM performance in multi-agent games by 22.1 percent through recursive modeling of other agents' reasoning and group-relative reinforcement learning.","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jiarui Gan, Jiexin Wang, Mengchen Zhao, Pengxu Yang, Yi Cai, Yidong He, Yutao Lai","submitted_at":"2026-05-06T13:35:14Z","abstract_excerpt":"While Large Language Models (LLMs) excel in certain reasoning tasks, they struggle in multi-agent games where the final outcome depends on the joint strategies of all agents. In multi-agent games, the non-stationarity of other agents brings significant challenges on the evaluation of the reasoning process and the credit assignment over multiple reasoning steps. Existing single-agent reinforcement learning (RL) approaches and their multi-agent extensions fail to address these challenges as they do not incorporate other agents in the reasoning process. In this work, we propose Strat-Reasoner, a "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Experimental results show that Strat-Reasoner substantially improves strategic abilities of underlying LLMs, achieving 22.1% average performance improvements across various multi-agent games.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the centralized Chain-of-Thought comparison module supplies unbiased, effective reward signals for intermediate reasoning sequences without introducing evaluation circularity or requiring hand-tuned thresholds that favor the proposed method.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Strat-Reasoner boosts LLMs' strategic performance in multi-agent games by 22.1% on average via recursive reasoning that includes other agents' thought processes and a centralized CoT evaluator for intermediate rewards.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Strat-Reasoner improves LLM performance in multi-agent games by 22.1 percent through recursive modeling of other agents' reasoning and group-relative reinforcement learning.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"b5ae241aac07cfe364bced591e61ca5dc97c507790b8fad1d8146427c0b5b4a8"},"source":{"id":"2605.04906","kind":"arxiv","version":2},"verdict":{"id":"85f771d2-7a4b-49bc-8922-e36bcc331a7d","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-08T18:25:47.205301Z","strongest_claim":"Experimental results show that Strat-Reasoner substantially improves strategic abilities of underlying LLMs, achieving 22.1% average performance improvements across various multi-agent games.","one_line_summary":"Strat-Reasoner boosts LLMs' strategic performance in multi-agent games by 22.1% on average via recursive reasoning that includes other agents' thought processes and a centralized CoT evaluator for intermediate rewards.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the centralized Chain-of-Thought comparison module supplies unbiased, effective reward signals for intermediate reasoning sequences without introducing evaluation circularity or requiring hand-tuned thresholds that favor the proposed method.","pith_extraction_headline":"Strat-Reasoner improves LLM performance in multi-agent games by 22.1 percent through recursive modeling of other agents' reasoning and group-relative reinforcement learning."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.04906/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-20T10:40:58.678339Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T22:01:23.639665Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T14:03:34.797473Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"660aa19132ef432a81225a326119d4dff6b9e4c7ef9e51077070810613b887bc"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"12137ea112bcb4f77d1a5600f9be83d309dfbf5d8d925625990081c1ecdbd74a"},"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":"2605.04906","created_at":"2026-05-26T02:04:12.138626+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.04906v2","created_at":"2026-05-26T02:04:12.138626+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.04906","created_at":"2026-05-26T02:04:12.138626+00:00"},{"alias_kind":"pith_short_12","alias_value":"3RCJZ5ZKJYWI","created_at":"2026-05-26T02:04:12.138626+00:00"},{"alias_kind":"pith_short_16","alias_value":"3RCJZ5ZKJYWIVHXJ","created_at":"2026-05-26T02:04:12.138626+00:00"},{"alias_kind":"pith_short_8","alias_value":"3RCJZ5ZK","created_at":"2026-05-26T02:04:12.138626+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3RCJZ5ZKJYWIVHXJDRAH6SA2XM","json":"https://pith.science/pith/3RCJZ5ZKJYWIVHXJDRAH6SA2XM.json","graph_json":"https://pith.science/api/pith-number/3RCJZ5ZKJYWIVHXJDRAH6SA2XM/graph.json","events_json":"https://pith.science/api/pith-number/3RCJZ5ZKJYWIVHXJDRAH6SA2XM/events.json","paper":"https://pith.science/paper/3RCJZ5ZK"},"agent_actions":{"view_html":"https://pith.science/pith/3RCJZ5ZKJYWIVHXJDRAH6SA2XM","download_json":"https://pith.science/pith/3RCJZ5ZKJYWIVHXJDRAH6SA2XM.json","view_paper":"https://pith.science/paper/3RCJZ5ZK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.04906&json=true","fetch_graph":"https://pith.science/api/pith-number/3RCJZ5ZKJYWIVHXJDRAH6SA2XM/graph.json","fetch_events":"https://pith.science/api/pith-number/3RCJZ5ZKJYWIVHXJDRAH6SA2XM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3RCJZ5ZKJYWIVHXJDRAH6SA2XM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3RCJZ5ZKJYWIVHXJDRAH6SA2XM/action/storage_attestation","attest_author":"https://pith.science/pith/3RCJZ5ZKJYWIVHXJDRAH6SA2XM/action/author_attestation","sign_citation":"https://pith.science/pith/3RCJZ5ZKJYWIVHXJDRAH6SA2XM/action/citation_signature","submit_replication":"https://pith.science/pith/3RCJZ5ZKJYWIVHXJDRAH6SA2XM/action/replication_record"}},"created_at":"2026-05-26T02:04:12.138626+00:00","updated_at":"2026-05-26T02:04:12.138626+00:00"}