{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BVQGL67QBSNCNCH7BC3ME5B74P","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":"336e0a9c7647277250c62c3de943c9635a57288917e24209a2b1b2589dfce52b","cross_cats_sorted":["cs.AI","cs.LG","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2025-04-21T07:03:54Z","title_canon_sha256":"61fdee7f5c822a2f7cf8d5c84aca2b5db9bf3e79c8c70b20d35e6db90d1ec21e"},"schema_version":"1.0","source":{"id":"2504.16129","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.16129","created_at":"2026-06-02T01:03:31Z"},{"alias_kind":"arxiv_version","alias_value":"2504.16129v5","created_at":"2026-06-02T01:03:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.16129","created_at":"2026-06-02T01:03:31Z"},{"alias_kind":"pith_short_12","alias_value":"BVQGL67QBSNC","created_at":"2026-06-02T01:03:31Z"},{"alias_kind":"pith_short_16","alias_value":"BVQGL67QBSNCNCH7","created_at":"2026-06-02T01:03:31Z"},{"alias_kind":"pith_short_8","alias_value":"BVQGL67Q","created_at":"2026-06-02T01:03:31Z"}],"graph_snapshots":[{"event_id":"sha256:5ba16e73c8d23c655fb5741672a71b7eeaad9cfdd10c52bf3e30342048fdfcbc","target":"graph","created_at":"2026-06-02T01:03:31Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2504.16129/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Model (LLM)-based Multi-Agent Systems (LaMAS) have demonstrated strong capabilities on complex agentic tasks requiring multifaceted reasoning and collaboration, from high-quality presentation generation to scientific research. Meanwhile, Reinforcement Learning (RL) is widely recognized for enhancing agent intelligence, but limited work has studied fine-tuning LaMAS with foundational RL techniques. Directly applying conventional Multi-Agent Reinforcement Learning (MARL) to LaMAS also introduces major challenges due to the unique mechanisms of LaMAS. To address these challenges, t","authors_text":"Jun Wang, Junwei Liao, Muning Wen, Weinan Zhang","cross_cats":["cs.AI","cs.LG","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2025-04-21T07:03:54Z","title":"MARFT: Multi-Agent Reinforcement Fine-Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.16129","kind":"arxiv","version":5},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c67e8aac68c5f472d671492d5a3f0b5a96410681c52a1a375d899f3672de4e54","target":"record","created_at":"2026-06-02T01:03:31Z","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":"336e0a9c7647277250c62c3de943c9635a57288917e24209a2b1b2589dfce52b","cross_cats_sorted":["cs.AI","cs.LG","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2025-04-21T07:03:54Z","title_canon_sha256":"61fdee7f5c822a2f7cf8d5c84aca2b5db9bf3e79c8c70b20d35e6db90d1ec21e"},"schema_version":"1.0","source":{"id":"2504.16129","kind":"arxiv","version":5}},"canonical_sha256":"0d6065fbf00c9a2688ff08b6c2743fe3c9af2d6ec2f973fcf9372591293719ce","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0d6065fbf00c9a2688ff08b6c2743fe3c9af2d6ec2f973fcf9372591293719ce","first_computed_at":"2026-06-02T01:03:31.278171Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T01:03:31.278171Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Rcrl6bpbiPNcaB8S/KKz3v18Nt8p+RwDvm/S/aEPbZcxVTGldroETaFI2aDuDJWC6WzbHY9Gm4kJKf54gW9gCA==","signature_status":"signed_v1","signed_at":"2026-06-02T01:03:31.278690Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.16129","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c67e8aac68c5f472d671492d5a3f0b5a96410681c52a1a375d899f3672de4e54","sha256:5ba16e73c8d23c655fb5741672a71b7eeaad9cfdd10c52bf3e30342048fdfcbc"],"state_sha256":"32e0dc2b0ab87a1b78ee3e7b8a1d5e78f102fdfcffe6bbaae6fffc02dfbfe717"}