{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4OBM5MV6U76SYN2T23BTVIB462","short_pith_number":"pith:4OBM5MV6","schema_version":"1.0","canonical_sha256":"e382ceb2bea7fd2c3753d6c33aa03cf6a2afdffd8b70a61dec527f0408ed69ae","source":{"kind":"arxiv","id":"2507.09495","version":1},"attestation_state":"computed","paper":{"title":"GenAI-based Multi-Agent Reinforcement Learning towards Distributed Agent Intelligence: A Generative-RL Agent Perspective","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.ET","cs.HC","cs.RO","cs.SY","eess.SY"],"primary_cat":"cs.AI","authors_text":"Hang Wang, Junshan Zhang","submitted_at":"2025-07-13T05:02:43Z","abstract_excerpt":"Multi-agent reinforcement learning faces fundamental challenges that conventional approaches have failed to overcome: exponentially growing joint action spaces, non-stationary environments where simultaneous learning creates moving targets, and partial observability that constrains coordination. Current methods remain reactive, employing stimulus-response mechanisms that fail when facing novel scenarios. We argue for a transformative paradigm shift from reactive to proactive multi-agent intelligence through generative AI-based reinforcement learning. This position advocates reconceptualizing 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":"2507.09495","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-13T05:02:43Z","cross_cats_sorted":["cs.ET","cs.HC","cs.RO","cs.SY","eess.SY"],"title_canon_sha256":"e0b9c2526072eef4a55d36388080237f80f38af2a37e273f32fdbdb2d67d5ce3","abstract_canon_sha256":"d10fc8d82ebd92146253cee7415ae76cf6587260bd2c3f71e323012ba50d8e95"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:36:10.063484Z","signature_b64":"/xnKlKx3a3klOmL8Ql6M86RUAFlIIsMiLt05F2zUymN/97M/aZ0IXqt6WSHAMDvQbZ9vIcXiRRz4L6JW1EJmCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e382ceb2bea7fd2c3753d6c33aa03cf6a2afdffd8b70a61dec527f0408ed69ae","last_reissued_at":"2026-07-05T11:36:10.062876Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:36:10.062876Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GenAI-based Multi-Agent Reinforcement Learning towards Distributed Agent Intelligence: A Generative-RL Agent Perspective","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.ET","cs.HC","cs.RO","cs.SY","eess.SY"],"primary_cat":"cs.AI","authors_text":"Hang Wang, Junshan Zhang","submitted_at":"2025-07-13T05:02:43Z","abstract_excerpt":"Multi-agent reinforcement learning faces fundamental challenges that conventional approaches have failed to overcome: exponentially growing joint action spaces, non-stationary environments where simultaneous learning creates moving targets, and partial observability that constrains coordination. Current methods remain reactive, employing stimulus-response mechanisms that fail when facing novel scenarios. We argue for a transformative paradigm shift from reactive to proactive multi-agent intelligence through generative AI-based reinforcement learning. This position advocates reconceptualizing a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.09495","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/2507.09495/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":"2507.09495","created_at":"2026-07-05T11:36:10.062959+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.09495v1","created_at":"2026-07-05T11:36:10.062959+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.09495","created_at":"2026-07-05T11:36:10.062959+00:00"},{"alias_kind":"pith_short_12","alias_value":"4OBM5MV6U76S","created_at":"2026-07-05T11:36:10.062959+00:00"},{"alias_kind":"pith_short_16","alias_value":"4OBM5MV6U76SYN2T","created_at":"2026-07-05T11:36:10.062959+00:00"},{"alias_kind":"pith_short_8","alias_value":"4OBM5MV6","created_at":"2026-07-05T11:36:10.062959+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.09682","citing_title":"Decision-Theoretic Safety Assessment of Persona-Driven Multi-Agent Systems in O-RAN","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4OBM5MV6U76SYN2T23BTVIB462","json":"https://pith.science/pith/4OBM5MV6U76SYN2T23BTVIB462.json","graph_json":"https://pith.science/api/pith-number/4OBM5MV6U76SYN2T23BTVIB462/graph.json","events_json":"https://pith.science/api/pith-number/4OBM5MV6U76SYN2T23BTVIB462/events.json","paper":"https://pith.science/paper/4OBM5MV6"},"agent_actions":{"view_html":"https://pith.science/pith/4OBM5MV6U76SYN2T23BTVIB462","download_json":"https://pith.science/pith/4OBM5MV6U76SYN2T23BTVIB462.json","view_paper":"https://pith.science/paper/4OBM5MV6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.09495&json=true","fetch_graph":"https://pith.science/api/pith-number/4OBM5MV6U76SYN2T23BTVIB462/graph.json","fetch_events":"https://pith.science/api/pith-number/4OBM5MV6U76SYN2T23BTVIB462/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4OBM5MV6U76SYN2T23BTVIB462/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4OBM5MV6U76SYN2T23BTVIB462/action/storage_attestation","attest_author":"https://pith.science/pith/4OBM5MV6U76SYN2T23BTVIB462/action/author_attestation","sign_citation":"https://pith.science/pith/4OBM5MV6U76SYN2T23BTVIB462/action/citation_signature","submit_replication":"https://pith.science/pith/4OBM5MV6U76SYN2T23BTVIB462/action/replication_record"}},"created_at":"2026-07-05T11:36:10.062959+00:00","updated_at":"2026-07-05T11:36:10.062959+00:00"}