{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:W2PSSXHXNSL4VTKRJNKTY5THN6","short_pith_number":"pith:W2PSSXHX","schema_version":"1.0","canonical_sha256":"b69f295cf76c97cacd514b553c76676f9f1a18f1af58c0d10e1c1c2499a729de","source":{"kind":"arxiv","id":"2503.02077","version":3},"attestation_state":"computed","paper":{"title":"M3HF: Multi-agent Reinforcement Learning from Multi-phase Human Feedback of Mixed Quality","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.MA","authors_text":"Fei Fang, Yali Du, Zhicheng Zhang, Ziyan Wang","submitted_at":"2025-03-03T21:58:10Z","abstract_excerpt":"Designing effective reward functions in multi-agent reinforcement learning (MARL) is a significant challenge, often leading to suboptimal or misaligned behaviors in complex, coordinated environments. We introduce Multi-agent Reinforcement Learning from Multi-phase Human Feedback of Mixed Quality ($\\text{M}^3\\text{HF}$), a novel framework that integrates multi-phase human feedback of mixed quality into the MARL training process. By involving humans with diverse expertise levels to provide iterative guidance, $\\text{M}^3\\text{HF}$ leverages both expert and non-expert feedback to continuously ref"},"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":"2503.02077","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2025-03-03T21:58:10Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"1d73d7e7339b405b6e14fa470580167910f7a712b5a8f2cf436dbfa10580fcfe","abstract_canon_sha256":"d44237d5fae8585e1e568b828c10e510b99a229e1b65a022cc0b2976a5eec507"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:19.877948Z","signature_b64":"hRqM9iDmS4lGs+419V9rvBBapsS7UwGfDP/fljRAvORYvB0q66Nqji0Vwza3E3SjgnbFKUIoB39G5pzpke8rCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b69f295cf76c97cacd514b553c76676f9f1a18f1af58c0d10e1c1c2499a729de","last_reissued_at":"2026-07-05T11:15:19.877473Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:19.877473Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"M3HF: Multi-agent Reinforcement Learning from Multi-phase Human Feedback of Mixed Quality","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.MA","authors_text":"Fei Fang, Yali Du, Zhicheng Zhang, Ziyan Wang","submitted_at":"2025-03-03T21:58:10Z","abstract_excerpt":"Designing effective reward functions in multi-agent reinforcement learning (MARL) is a significant challenge, often leading to suboptimal or misaligned behaviors in complex, coordinated environments. We introduce Multi-agent Reinforcement Learning from Multi-phase Human Feedback of Mixed Quality ($\\text{M}^3\\text{HF}$), a novel framework that integrates multi-phase human feedback of mixed quality into the MARL training process. By involving humans with diverse expertise levels to provide iterative guidance, $\\text{M}^3\\text{HF}$ leverages both expert and non-expert feedback to continuously ref"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.02077","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/2503.02077/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":"2503.02077","created_at":"2026-07-05T11:15:19.877530+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.02077v3","created_at":"2026-07-05T11:15:19.877530+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.02077","created_at":"2026-07-05T11:15:19.877530+00:00"},{"alias_kind":"pith_short_12","alias_value":"W2PSSXHXNSL4","created_at":"2026-07-05T11:15:19.877530+00:00"},{"alias_kind":"pith_short_16","alias_value":"W2PSSXHXNSL4VTKR","created_at":"2026-07-05T11:15:19.877530+00:00"},{"alias_kind":"pith_short_8","alias_value":"W2PSSXHX","created_at":"2026-07-05T11:15:19.877530+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.12655","citing_title":"Robust Instruction Compliance in Cooperative Multi-Agent Reinforcement Learning","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2511.20857","citing_title":"Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory","ref_index":65,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W2PSSXHXNSL4VTKRJNKTY5THN6","json":"https://pith.science/pith/W2PSSXHXNSL4VTKRJNKTY5THN6.json","graph_json":"https://pith.science/api/pith-number/W2PSSXHXNSL4VTKRJNKTY5THN6/graph.json","events_json":"https://pith.science/api/pith-number/W2PSSXHXNSL4VTKRJNKTY5THN6/events.json","paper":"https://pith.science/paper/W2PSSXHX"},"agent_actions":{"view_html":"https://pith.science/pith/W2PSSXHXNSL4VTKRJNKTY5THN6","download_json":"https://pith.science/pith/W2PSSXHXNSL4VTKRJNKTY5THN6.json","view_paper":"https://pith.science/paper/W2PSSXHX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.02077&json=true","fetch_graph":"https://pith.science/api/pith-number/W2PSSXHXNSL4VTKRJNKTY5THN6/graph.json","fetch_events":"https://pith.science/api/pith-number/W2PSSXHXNSL4VTKRJNKTY5THN6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W2PSSXHXNSL4VTKRJNKTY5THN6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W2PSSXHXNSL4VTKRJNKTY5THN6/action/storage_attestation","attest_author":"https://pith.science/pith/W2PSSXHXNSL4VTKRJNKTY5THN6/action/author_attestation","sign_citation":"https://pith.science/pith/W2PSSXHXNSL4VTKRJNKTY5THN6/action/citation_signature","submit_replication":"https://pith.science/pith/W2PSSXHXNSL4VTKRJNKTY5THN6/action/replication_record"}},"created_at":"2026-07-05T11:15:19.877530+00:00","updated_at":"2026-07-05T11:15:19.877530+00:00"}