{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6XXJD7AQEAYECFU25YYJ7E4UGO","short_pith_number":"pith:6XXJD7AQ","schema_version":"1.0","canonical_sha256":"f5ee91fc10203041169aee309f939433986441060954ed48ce4d01feb7df809d","source":{"kind":"arxiv","id":"2410.22304","version":1},"attestation_state":"computed","paper":{"title":"Flow-DPO: Improving LLM Mathematical Reasoning through Online Multi-Agent Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Paul Mineiro, Yihe Deng","submitted_at":"2024-10-29T17:50:31Z","abstract_excerpt":"Mathematical reasoning is a crucial capability for Large Language Models (LLMs), yet generating detailed and accurate reasoning traces remains a significant challenge. This paper introduces a novel approach to produce high-quality reasoning traces for LLM fine-tuning using online learning \\textbf{Flows}. Our method employs an incremental output production Flow, where component LLMs collaboratively construct solutions through iterative communication. We train the Flow using online Direct Preference Optimization (DPO) learning with rollouts, generating DPO pairs for each training example and upd"},"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":"2410.22304","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-29T17:50:31Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7ffee1c1aada5baf108e01cbe57a5cf7a10e4a5142721c926285da2ed6428216","abstract_canon_sha256":"9c38e5a519a526f773c99f78711966f1ae8ecac446c05b4062900e2326844852"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:28:07.184484Z","signature_b64":"kGhzrDfazo9bFBGPKX3SLh25NUkCJUDPSjl5N4nPTHOa0GxllXTafqLNwW3ABgQAeh3o3ct5LLhPITiK4DsEDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5ee91fc10203041169aee309f939433986441060954ed48ce4d01feb7df809d","last_reissued_at":"2026-07-05T09:28:07.184010Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:28:07.184010Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Flow-DPO: Improving LLM Mathematical Reasoning through Online Multi-Agent Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Paul Mineiro, Yihe Deng","submitted_at":"2024-10-29T17:50:31Z","abstract_excerpt":"Mathematical reasoning is a crucial capability for Large Language Models (LLMs), yet generating detailed and accurate reasoning traces remains a significant challenge. This paper introduces a novel approach to produce high-quality reasoning traces for LLM fine-tuning using online learning \\textbf{Flows}. Our method employs an incremental output production Flow, where component LLMs collaboratively construct solutions through iterative communication. We train the Flow using online Direct Preference Optimization (DPO) learning with rollouts, generating DPO pairs for each training example and upd"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.22304","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/2410.22304/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":"2410.22304","created_at":"2026-07-05T09:28:07.184067+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.22304v1","created_at":"2026-07-05T09:28:07.184067+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.22304","created_at":"2026-07-05T09:28:07.184067+00:00"},{"alias_kind":"pith_short_12","alias_value":"6XXJD7AQEAYE","created_at":"2026-07-05T09:28:07.184067+00:00"},{"alias_kind":"pith_short_16","alias_value":"6XXJD7AQEAYECFU2","created_at":"2026-07-05T09:28:07.184067+00:00"},{"alias_kind":"pith_short_8","alias_value":"6XXJD7AQ","created_at":"2026-07-05T09:28:07.184067+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11470","citing_title":"The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2504.19678","citing_title":"From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review","ref_index":205,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6XXJD7AQEAYECFU25YYJ7E4UGO","json":"https://pith.science/pith/6XXJD7AQEAYECFU25YYJ7E4UGO.json","graph_json":"https://pith.science/api/pith-number/6XXJD7AQEAYECFU25YYJ7E4UGO/graph.json","events_json":"https://pith.science/api/pith-number/6XXJD7AQEAYECFU25YYJ7E4UGO/events.json","paper":"https://pith.science/paper/6XXJD7AQ"},"agent_actions":{"view_html":"https://pith.science/pith/6XXJD7AQEAYECFU25YYJ7E4UGO","download_json":"https://pith.science/pith/6XXJD7AQEAYECFU25YYJ7E4UGO.json","view_paper":"https://pith.science/paper/6XXJD7AQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.22304&json=true","fetch_graph":"https://pith.science/api/pith-number/6XXJD7AQEAYECFU25YYJ7E4UGO/graph.json","fetch_events":"https://pith.science/api/pith-number/6XXJD7AQEAYECFU25YYJ7E4UGO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6XXJD7AQEAYECFU25YYJ7E4UGO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6XXJD7AQEAYECFU25YYJ7E4UGO/action/storage_attestation","attest_author":"https://pith.science/pith/6XXJD7AQEAYECFU25YYJ7E4UGO/action/author_attestation","sign_citation":"https://pith.science/pith/6XXJD7AQEAYECFU25YYJ7E4UGO/action/citation_signature","submit_replication":"https://pith.science/pith/6XXJD7AQEAYECFU25YYJ7E4UGO/action/replication_record"}},"created_at":"2026-07-05T09:28:07.184067+00:00","updated_at":"2026-07-05T09:28:07.184067+00:00"}