{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:3RCJZ5ZKJYWIVHXJDRAH6SA2XM","short_pith_number":"pith:3RCJZ5ZK","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"},"canonical_sha256":"dc449cf72a4e2c8a9ee91c407f481abb36f918b2c16267b105322c89e6a60d55","source":{"kind":"arxiv","id":"2605.04906","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.04906","created_at":"2026-05-26T02:04:12Z"},{"alias_kind":"arxiv_version","alias_value":"2605.04906v2","created_at":"2026-05-26T02:04:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.04906","created_at":"2026-05-26T02:04:12Z"},{"alias_kind":"pith_short_12","alias_value":"3RCJZ5ZKJYWI","created_at":"2026-05-26T02:04:12Z"},{"alias_kind":"pith_short_16","alias_value":"3RCJZ5ZKJYWIVHXJ","created_at":"2026-05-26T02:04:12Z"},{"alias_kind":"pith_short_8","alias_value":"3RCJZ5ZK","created_at":"2026-05-26T02:04:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:3RCJZ5ZKJYWIVHXJDRAH6SA2XM","target":"record","payload":{"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"},"canonical_sha256":"dc449cf72a4e2c8a9ee91c407f481abb36f918b2c16267b105322c89e6a60d55","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"},"source_kind":"arxiv","source_id":"2605.04906","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-26T02:04:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/XTHIM5o2JCBAGY+b3cBZnkiVPMtHYDWGNZPojqW9FDa8ljypie37xK7KoSzKHkp896b3RM/Vjjw06Z4QK4hDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T12:56:41.035078Z"},"content_sha256":"4b7210466093a08f21db2f15d1e0dcb53df75051670b22258024fb1b8d9d1f01","schema_version":"1.0","event_id":"sha256:4b7210466093a08f21db2f15d1e0dcb53df75051670b22258024fb1b8d9d1f01"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:3RCJZ5ZKJYWIVHXJDRAH6SA2XM","target":"graph","payload":{"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"},"verdict_id":"85f771d2-7a4b-49bc-8922-e36bcc331a7d"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-26T02:04:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BfXIT/JXWOhq/8oIdXSqH+9odjUSL44r/MVEoIzKnfugxlpGCS+UdVAD9zkevhJbtEHgYjnZqeFAiPw/dHp0DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T12:56:41.035579Z"},"content_sha256":"dfa4256b4302ea875230ebbfe39c35e5aef18f9e834ba5aacd24d3dfcb22abd2","schema_version":"1.0","event_id":"sha256:dfa4256b4302ea875230ebbfe39c35e5aef18f9e834ba5aacd24d3dfcb22abd2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3RCJZ5ZKJYWIVHXJDRAH6SA2XM/bundle.json","state_url":"https://pith.science/pith/3RCJZ5ZKJYWIVHXJDRAH6SA2XM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3RCJZ5ZKJYWIVHXJDRAH6SA2XM/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-09T12:56:41Z","links":{"resolver":"https://pith.science/pith/3RCJZ5ZKJYWIVHXJDRAH6SA2XM","bundle":"https://pith.science/pith/3RCJZ5ZKJYWIVHXJDRAH6SA2XM/bundle.json","state":"https://pith.science/pith/3RCJZ5ZKJYWIVHXJDRAH6SA2XM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3RCJZ5ZKJYWIVHXJDRAH6SA2XM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:3RCJZ5ZKJYWIVHXJDRAH6SA2XM","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"6682c5ba6ba04186213d5e48b22c9dd04edd20d962feaeb17b7ae76ee46e8c40","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-06T13:35:14Z","title_canon_sha256":"5099b995350a9d628d4c1d02b5beb97eae7363ad3d2470883cf01cd75ac79321"},"schema_version":"1.0","source":{"id":"2605.04906","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.04906","created_at":"2026-05-26T02:04:12Z"},{"alias_kind":"arxiv_version","alias_value":"2605.04906v2","created_at":"2026-05-26T02:04:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.04906","created_at":"2026-05-26T02:04:12Z"},{"alias_kind":"pith_short_12","alias_value":"3RCJZ5ZKJYWI","created_at":"2026-05-26T02:04:12Z"},{"alias_kind":"pith_short_16","alias_value":"3RCJZ5ZKJYWIVHXJ","created_at":"2026-05-26T02:04:12Z"},{"alias_kind":"pith_short_8","alias_value":"3RCJZ5ZK","created_at":"2026-05-26T02:04:12Z"}],"graph_snapshots":[{"event_id":"sha256:dfa4256b4302ea875230ebbfe39c35e5aef18f9e834ba5aacd24d3dfcb22abd2","target":"graph","created_at":"2026-05-26T02:04:12Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","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."}],"snapshot_sha256":"b5ae241aac07cfe364bced591e61ca5dc97c507790b8fad1d8146427c0b5b4a8"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"12137ea112bcb4f77d1a5600f9be83d309dfbf5d8d925625990081c1ecdbd74a"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"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"}],"endpoint":"/pith/2605.04906/integrity.json","findings":[],"snapshot_sha256":"660aa19132ef432a81225a326119d4dff6b9e4c7ef9e51077070810613b887bc","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Jiarui Gan, Jiexin Wang, Mengchen Zhao, Pengxu Yang, Yi Cai, Yidong He, Yutao Lai","cross_cats":[],"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.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-06T13:35:14Z","title":"Strat-Reasoner: Reinforcing Strategic Reasoning of LLMs in Multi-Agent Games"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.04906","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-08T18:25:47.205301Z","id":"85f771d2-7a4b-49bc-8922-e36bcc331a7d","model_set":{"reader":"grok-4.3"},"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","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.","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.","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."}},"verdict_id":"85f771d2-7a4b-49bc-8922-e36bcc331a7d"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4b7210466093a08f21db2f15d1e0dcb53df75051670b22258024fb1b8d9d1f01","target":"record","created_at":"2026-05-26T02:04:12Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"6682c5ba6ba04186213d5e48b22c9dd04edd20d962feaeb17b7ae76ee46e8c40","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-06T13:35:14Z","title_canon_sha256":"5099b995350a9d628d4c1d02b5beb97eae7363ad3d2470883cf01cd75ac79321"},"schema_version":"1.0","source":{"id":"2605.04906","kind":"arxiv","version":2}},"canonical_sha256":"dc449cf72a4e2c8a9ee91c407f481abb36f918b2c16267b105322c89e6a60d55","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dc449cf72a4e2c8a9ee91c407f481abb36f918b2c16267b105322c89e6a60d55","first_computed_at":"2026-05-26T02:04:12.138521Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T02:04:12.138521Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IwEGkSZ0UlTK1BhrFhJlJMtui8nTD/IauppLyn2XAon8E4Gqz+MPhdFwkXaCrCkwZeSuntTP9f9367cPTgsRCw==","signature_status":"signed_v1","signed_at":"2026-05-26T02:04:12.139200Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.04906","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4b7210466093a08f21db2f15d1e0dcb53df75051670b22258024fb1b8d9d1f01","sha256:dfa4256b4302ea875230ebbfe39c35e5aef18f9e834ba5aacd24d3dfcb22abd2"],"state_sha256":"6861718e984f16c6d50a9e1b977c4b9b7b7e4150dba33678ded0ffb960610ef4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FAm6+WIQEMvqEfJpj7fBv7NT5nyfyq0f9GFPWFNZ4xOmUMxL6SopR64Y3mWONvyRe+ieBy0wcVITqTg37GMjCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T12:56:41.037804Z","bundle_sha256":"0438f5aed2cdbcd2e3875550782d2f59d909ad6103dc34bae6756964564e7425"}}