{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DW67FVENWFBPRRKPCLGKASVKQS","short_pith_number":"pith:DW67FVEN","schema_version":"1.0","canonical_sha256":"1dbdf2d48db142f8c54f12cca04aaa84a1940dcaa7b972fc1a020108e6f4a474","source":{"kind":"arxiv","id":"2503.02390","version":3},"attestation_state":"computed","paper":{"title":"ReSo: A Reward-driven Self-organizing LLM-based Multi-Agent System for Reasoning Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.MA","authors_text":"Hejia Geng, Heng Zhou, Lei Bai, Li Kang, Xiangyuan Xue, Yiran Qin, Zhenfei Yin, Zhiyong Wang","submitted_at":"2025-03-04T08:28:04Z","abstract_excerpt":"Multi-agent systems (MAS) have emerged as a promising approach for enhancing the reasoning capabilities of large language models in complex problem-solving; however, current MAS frameworks suffer from poor flexibility and scalability with underdeveloped optimization strategies. To address these challenges, we propose ReSo, which integrates task graph generation with a reward-driven two-stage agent selection process centered on our Collaborative Reward Model that provides fine-grained reward signals to optimize MAS cooperation. We also introduce an automated data synthesis framework for generat"},"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":"2503.02390","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2025-03-04T08:28:04Z","cross_cats_sorted":[],"title_canon_sha256":"565744ba9821ee459b4330cd1e2bdab66c53645338d524a6c1c7e87251993e4a","abstract_canon_sha256":"b8bd1bfe73207ae57faef90b903db20a0998041f98e1c9f9d322b840eec17e74"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:28.824960Z","signature_b64":"SaHb+eX8oRWs/2w2UPl3sQEGDrvFVzb22UjHjWUDxHwoj8Ozz1uLqDTw6KadPm3Lj3HddTRZ+/YSx0Ei8isVCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1dbdf2d48db142f8c54f12cca04aaa84a1940dcaa7b972fc1a020108e6f4a474","last_reissued_at":"2026-07-05T11:12:28.824457Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:28.824457Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ReSo: A Reward-driven Self-organizing LLM-based Multi-Agent System for Reasoning Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.MA","authors_text":"Hejia Geng, Heng Zhou, Lei Bai, Li Kang, Xiangyuan Xue, Yiran Qin, Zhenfei Yin, Zhiyong Wang","submitted_at":"2025-03-04T08:28:04Z","abstract_excerpt":"Multi-agent systems (MAS) have emerged as a promising approach for enhancing the reasoning capabilities of large language models in complex problem-solving; however, current MAS frameworks suffer from poor flexibility and scalability with underdeveloped optimization strategies. To address these challenges, we propose ReSo, which integrates task graph generation with a reward-driven two-stage agent selection process centered on our Collaborative Reward Model that provides fine-grained reward signals to optimize MAS cooperation. We also introduce an automated data synthesis framework for generat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.02390","kind":"arxiv","version":3},"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/2503.02390/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":"2503.02390","created_at":"2026-07-05T11:12:28.824522+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.02390v3","created_at":"2026-07-05T11:12:28.824522+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.02390","created_at":"2026-07-05T11:12:28.824522+00:00"},{"alias_kind":"pith_short_12","alias_value":"DW67FVENWFBP","created_at":"2026-07-05T11:12:28.824522+00:00"},{"alias_kind":"pith_short_16","alias_value":"DW67FVENWFBPRRKP","created_at":"2026-07-05T11:12:28.824522+00:00"},{"alias_kind":"pith_short_8","alias_value":"DW67FVEN","created_at":"2026-07-05T11:12:28.824522+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.18133","citing_title":"Multi-Agent Systems: From Classical Paradigms to Large Foundation Model-Enabled Futures","ref_index":84,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DW67FVENWFBPRRKPCLGKASVKQS","json":"https://pith.science/pith/DW67FVENWFBPRRKPCLGKASVKQS.json","graph_json":"https://pith.science/api/pith-number/DW67FVENWFBPRRKPCLGKASVKQS/graph.json","events_json":"https://pith.science/api/pith-number/DW67FVENWFBPRRKPCLGKASVKQS/events.json","paper":"https://pith.science/paper/DW67FVEN"},"agent_actions":{"view_html":"https://pith.science/pith/DW67FVENWFBPRRKPCLGKASVKQS","download_json":"https://pith.science/pith/DW67FVENWFBPRRKPCLGKASVKQS.json","view_paper":"https://pith.science/paper/DW67FVEN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.02390&json=true","fetch_graph":"https://pith.science/api/pith-number/DW67FVENWFBPRRKPCLGKASVKQS/graph.json","fetch_events":"https://pith.science/api/pith-number/DW67FVENWFBPRRKPCLGKASVKQS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DW67FVENWFBPRRKPCLGKASVKQS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DW67FVENWFBPRRKPCLGKASVKQS/action/storage_attestation","attest_author":"https://pith.science/pith/DW67FVENWFBPRRKPCLGKASVKQS/action/author_attestation","sign_citation":"https://pith.science/pith/DW67FVENWFBPRRKPCLGKASVKQS/action/citation_signature","submit_replication":"https://pith.science/pith/DW67FVENWFBPRRKPCLGKASVKQS/action/replication_record"}},"created_at":"2026-07-05T11:12:28.824522+00:00","updated_at":"2026-07-05T11:12:28.824522+00:00"}