{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:25FCK7VRDCBUS4TUJZ6OCCHQUM","short_pith_number":"pith:25FCK7VR","schema_version":"1.0","canonical_sha256":"d74a257eb118834972744e7ce108f0a30b70d6b6cdd929b337127a7779b939ad","source":{"kind":"arxiv","id":"2506.00577","version":1},"attestation_state":"computed","paper":{"title":"Reasoning Like an Economist: Post-Training on Economic Problems Induces Strategic Generalization in LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.GT","cs.MA"],"primary_cat":"cs.AI","authors_text":"Dayiheng Liu, Kexin Yang, Linfeng Zhang, Shaobo Wang, Xiangqi Jin, Xingyu Dong, Xingzhang Ren, Yifang Chen, Yue Min, Yufa Zhou","submitted_at":"2025-05-31T14:22:40Z","abstract_excerpt":"Directly training Large Language Models (LLMs) for Multi-Agent Systems (MAS) remains challenging due to intricate reward modeling, dynamic agent interactions, and demanding generalization requirements. This paper explores whether post-training techniques, specifically Supervised Fine-Tuning (SFT) and Reinforcement Learning with Verifiable Rewards (RLVR), can effectively $\\textit{generalize}$ to multi-agent scenarios. We use economic reasoning as a testbed, leveraging its strong foundations in mathematics and game theory, its demand for structured analytical reasoning, and its relevance to real"},"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":"2506.00577","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-31T14:22:40Z","cross_cats_sorted":["cs.CL","cs.GT","cs.MA"],"title_canon_sha256":"71cc0182dd17ddea507a19b74481635cdad52bee74023f190ed1b59bf6ad13cb","abstract_canon_sha256":"e19fe3ba2614c6703175f1dcd0e89570edb12f5ea12475bb049291331bc66cd4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:37.260593Z","signature_b64":"XjrEimTFvTk2N8cqfzprBtuMhu+YUeXpvTT0MSbctwJDMsXfe27MNWudKwwEkm+eewVUzA0sSg81D5QLeguXAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d74a257eb118834972744e7ce108f0a30b70d6b6cdd929b337127a7779b939ad","last_reissued_at":"2026-07-05T11:13:37.260087Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:37.260087Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reasoning Like an Economist: Post-Training on Economic Problems Induces Strategic Generalization in LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.GT","cs.MA"],"primary_cat":"cs.AI","authors_text":"Dayiheng Liu, Kexin Yang, Linfeng Zhang, Shaobo Wang, Xiangqi Jin, Xingyu Dong, Xingzhang Ren, Yifang Chen, Yue Min, Yufa Zhou","submitted_at":"2025-05-31T14:22:40Z","abstract_excerpt":"Directly training Large Language Models (LLMs) for Multi-Agent Systems (MAS) remains challenging due to intricate reward modeling, dynamic agent interactions, and demanding generalization requirements. This paper explores whether post-training techniques, specifically Supervised Fine-Tuning (SFT) and Reinforcement Learning with Verifiable Rewards (RLVR), can effectively $\\textit{generalize}$ to multi-agent scenarios. We use economic reasoning as a testbed, leveraging its strong foundations in mathematics and game theory, its demand for structured analytical reasoning, and its relevance to real"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00577","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/2506.00577/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":"2506.00577","created_at":"2026-07-05T11:13:37.260148+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.00577v1","created_at":"2026-07-05T11:13:37.260148+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00577","created_at":"2026-07-05T11:13:37.260148+00:00"},{"alias_kind":"pith_short_12","alias_value":"25FCK7VRDCBU","created_at":"2026-07-05T11:13:37.260148+00:00"},{"alias_kind":"pith_short_16","alias_value":"25FCK7VRDCBUS4TU","created_at":"2026-07-05T11:13:37.260148+00:00"},{"alias_kind":"pith_short_8","alias_value":"25FCK7VR","created_at":"2026-07-05T11:13:37.260148+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/25FCK7VRDCBUS4TUJZ6OCCHQUM","json":"https://pith.science/pith/25FCK7VRDCBUS4TUJZ6OCCHQUM.json","graph_json":"https://pith.science/api/pith-number/25FCK7VRDCBUS4TUJZ6OCCHQUM/graph.json","events_json":"https://pith.science/api/pith-number/25FCK7VRDCBUS4TUJZ6OCCHQUM/events.json","paper":"https://pith.science/paper/25FCK7VR"},"agent_actions":{"view_html":"https://pith.science/pith/25FCK7VRDCBUS4TUJZ6OCCHQUM","download_json":"https://pith.science/pith/25FCK7VRDCBUS4TUJZ6OCCHQUM.json","view_paper":"https://pith.science/paper/25FCK7VR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.00577&json=true","fetch_graph":"https://pith.science/api/pith-number/25FCK7VRDCBUS4TUJZ6OCCHQUM/graph.json","fetch_events":"https://pith.science/api/pith-number/25FCK7VRDCBUS4TUJZ6OCCHQUM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/25FCK7VRDCBUS4TUJZ6OCCHQUM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/25FCK7VRDCBUS4TUJZ6OCCHQUM/action/storage_attestation","attest_author":"https://pith.science/pith/25FCK7VRDCBUS4TUJZ6OCCHQUM/action/author_attestation","sign_citation":"https://pith.science/pith/25FCK7VRDCBUS4TUJZ6OCCHQUM/action/citation_signature","submit_replication":"https://pith.science/pith/25FCK7VRDCBUS4TUJZ6OCCHQUM/action/replication_record"}},"created_at":"2026-07-05T11:13:37.260148+00:00","updated_at":"2026-07-05T11:13:37.260148+00:00"}