{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KX6HCDZLR45NSYEIR43T24XHGR","short_pith_number":"pith:KX6HCDZL","schema_version":"1.0","canonical_sha256":"55fc710f2b8f3ad960888f373d72e7346e67fb0136f195c218d6cd0ebef31a85","source":{"kind":"arxiv","id":"2501.05707","version":2},"attestation_state":"computed","paper":{"title":"Multiagent Finetuning: Self Improvement with Diverse Reasoning Chains","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Antonio Torralba, Igor Mordatch, Joshua B. Tenenbaum, Shuang Li, Vighnesh Subramaniam, Yilun Du","submitted_at":"2025-01-10T04:35:46Z","abstract_excerpt":"Large language models (LLMs) have achieved remarkable performance in recent years but are fundamentally limited by the underlying training data. To improve models beyond the training data, recent works have explored how LLMs can be used to generate synthetic data for autonomous self-improvement. However, successive steps of self-improvement can reach a point of diminishing returns. In this work, we propose a complementary approach towards self-improvement where finetuning is applied to a multiagent society of language models. A group of language models, all starting from the same base model, 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":false},"canonical_record":{"source":{"id":"2501.05707","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-10T04:35:46Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"8f3b48668bd014f005283a1f7c0bdfff135a6aa0243ba3e6f7961d540c4cff8d","abstract_canon_sha256":"48f0a0532369d00e6a6d9b50c7da5e11239fe50ecd514dd687deedfed43fcf11"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:22:55.522214Z","signature_b64":"aDjlIrkpd+eXb8veoRgjWlxZyIZKSw3Zg3xF8f8YmHwaSNaIVC7PwwQYb8du7ISBRrEHyzozYqyw6qdotkWwCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"55fc710f2b8f3ad960888f373d72e7346e67fb0136f195c218d6cd0ebef31a85","last_reissued_at":"2026-07-05T10:22:55.521539Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:22:55.521539Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multiagent Finetuning: Self Improvement with Diverse Reasoning Chains","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Antonio Torralba, Igor Mordatch, Joshua B. Tenenbaum, Shuang Li, Vighnesh Subramaniam, Yilun Du","submitted_at":"2025-01-10T04:35:46Z","abstract_excerpt":"Large language models (LLMs) have achieved remarkable performance in recent years but are fundamentally limited by the underlying training data. To improve models beyond the training data, recent works have explored how LLMs can be used to generate synthetic data for autonomous self-improvement. However, successive steps of self-improvement can reach a point of diminishing returns. In this work, we propose a complementary approach towards self-improvement where finetuning is applied to a multiagent society of language models. A group of language models, all starting from the same base model, a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.05707","kind":"arxiv","version":2},"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/2501.05707/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":"2501.05707","created_at":"2026-07-05T10:22:55.521630+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.05707v2","created_at":"2026-07-05T10:22:55.521630+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.05707","created_at":"2026-07-05T10:22:55.521630+00:00"},{"alias_kind":"pith_short_12","alias_value":"KX6HCDZLR45N","created_at":"2026-07-05T10:22:55.521630+00:00"},{"alias_kind":"pith_short_16","alias_value":"KX6HCDZLR45NSYEI","created_at":"2026-07-05T10:22:55.521630+00:00"},{"alias_kind":"pith_short_8","alias_value":"KX6HCDZL","created_at":"2026-07-05T10:22:55.521630+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.02859","citing_title":"Economy of Minds: Emerging Multi-Agent Intelligence with Economic Interactions","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29425","citing_title":"Mixture of Debaters: Learn to Debate at Architectural Level in Multi-Agent Reasoning","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15207","citing_title":"TeamTR: Trust-Region Fine-Tuning for Multi-Agent LLM Coordination","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2510.05174","citing_title":"Emergent Coordination in Multi-Agent Language Models","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2601.21972","citing_title":"Learning Decentralized LLM Collaboration with Multi-Agent Actor Critic","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2508.07407","citing_title":"A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems","ref_index":92,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11117","citing_title":"GRAFT-ATHENA: Self-Improving Agentic Teams for Autonomous Discovery and Evolutionary Numerical Algorithms","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2512.13564","citing_title":"Memory in the Age of AI Agents","ref_index":72,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12195","citing_title":"Representing expertise accelerates learning from pedagogical interaction data","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KX6HCDZLR45NSYEIR43T24XHGR","json":"https://pith.science/pith/KX6HCDZLR45NSYEIR43T24XHGR.json","graph_json":"https://pith.science/api/pith-number/KX6HCDZLR45NSYEIR43T24XHGR/graph.json","events_json":"https://pith.science/api/pith-number/KX6HCDZLR45NSYEIR43T24XHGR/events.json","paper":"https://pith.science/paper/KX6HCDZL"},"agent_actions":{"view_html":"https://pith.science/pith/KX6HCDZLR45NSYEIR43T24XHGR","download_json":"https://pith.science/pith/KX6HCDZLR45NSYEIR43T24XHGR.json","view_paper":"https://pith.science/paper/KX6HCDZL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.05707&json=true","fetch_graph":"https://pith.science/api/pith-number/KX6HCDZLR45NSYEIR43T24XHGR/graph.json","fetch_events":"https://pith.science/api/pith-number/KX6HCDZLR45NSYEIR43T24XHGR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KX6HCDZLR45NSYEIR43T24XHGR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KX6HCDZLR45NSYEIR43T24XHGR/action/storage_attestation","attest_author":"https://pith.science/pith/KX6HCDZLR45NSYEIR43T24XHGR/action/author_attestation","sign_citation":"https://pith.science/pith/KX6HCDZLR45NSYEIR43T24XHGR/action/citation_signature","submit_replication":"https://pith.science/pith/KX6HCDZLR45NSYEIR43T24XHGR/action/replication_record"}},"created_at":"2026-07-05T10:22:55.521630+00:00","updated_at":"2026-07-05T10:22:55.521630+00:00"}