{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:AKUB4K2ZUMQXQKMIW7WHZF3VR4","short_pith_number":"pith:AKUB4K2Z","schema_version":"1.0","canonical_sha256":"02a81e2b59a321782988b7ec7c97758f1d1f6d24e3faca50f64a9f84188d5231","source":{"kind":"arxiv","id":"2608.08604","version":1},"attestation_state":"computed","paper":{"title":"Multi-Agent Reinforcement Learning via Agent-Specific Preference","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ni Mu, Qing-Shan Jia, Yao Luan, Yiqin Yang","submitted_at":"2026-08-09T09:38:41Z","abstract_excerpt":"Multi-agent reinforcement learning (MARL) is a powerful framework for solving complex collaborative tasks, but it relies heavily on well-defined global reward functions. Designing such rewards is challenging, especially in systems with heterogeneous agents, where a single scalar objective may fail to capture diverse behaviors. In this paper, we introduce Multi-AGent Preference-Integrated lEarning (MAGPIE), which addresses these challenges through agent-specific preference modeling. Each agent is evaluated by a dedicated expert through preference signals, eliminating the need for global evaluat"},"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":"2608.08604","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-09T09:38:41Z","cross_cats_sorted":[],"title_canon_sha256":"a8e131a886012903601f47bc9c1bb37068bb6b206e4b722d63f87443867e4453","abstract_canon_sha256":"de2f4fc03b6689c437677b8d34726465baa3f01064564659786fb3625a68dba4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-11T01:23:08.096510Z","signature_b64":"V0pwcSOwOCo6eYhegcwg5HjsE15+E/nrnjGbiRRQNv+EqsKl5QgFRfq3DJSzAtSHhgPvm2l1qgf07QnMN2M5Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"02a81e2b59a321782988b7ec7c97758f1d1f6d24e3faca50f64a9f84188d5231","last_reissued_at":"2026-08-11T01:23:08.094052Z","signature_status":"signed_v1","first_computed_at":"2026-08-11T01:23:08.094052Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Agent Reinforcement Learning via Agent-Specific Preference","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ni Mu, Qing-Shan Jia, Yao Luan, Yiqin Yang","submitted_at":"2026-08-09T09:38:41Z","abstract_excerpt":"Multi-agent reinforcement learning (MARL) is a powerful framework for solving complex collaborative tasks, but it relies heavily on well-defined global reward functions. Designing such rewards is challenging, especially in systems with heterogeneous agents, where a single scalar objective may fail to capture diverse behaviors. In this paper, we introduce Multi-AGent Preference-Integrated lEarning (MAGPIE), which addresses these challenges through agent-specific preference modeling. Each agent is evaluated by a dedicated expert through preference signals, eliminating the need for global evaluat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.08604","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/2608.08604/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":"2608.08604","created_at":"2026-08-11T01:23:08.094805+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.08604v1","created_at":"2026-08-11T01:23:08.094805+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.08604","created_at":"2026-08-11T01:23:08.094805+00:00"},{"alias_kind":"pith_short_12","alias_value":"AKUB4K2ZUMQX","created_at":"2026-08-11T01:23:08.094805+00:00"},{"alias_kind":"pith_short_16","alias_value":"AKUB4K2ZUMQXQKMI","created_at":"2026-08-11T01:23:08.094805+00:00"},{"alias_kind":"pith_short_8","alias_value":"AKUB4K2Z","created_at":"2026-08-11T01:23:08.094805+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AKUB4K2ZUMQXQKMIW7WHZF3VR4","json":"https://pith.science/pith/AKUB4K2ZUMQXQKMIW7WHZF3VR4.json","graph_json":"https://pith.science/api/pith-number/AKUB4K2ZUMQXQKMIW7WHZF3VR4/graph.json","events_json":"https://pith.science/api/pith-number/AKUB4K2ZUMQXQKMIW7WHZF3VR4/events.json","paper":"https://pith.science/paper/AKUB4K2Z"},"agent_actions":{"view_html":"https://pith.science/pith/AKUB4K2ZUMQXQKMIW7WHZF3VR4","download_json":"https://pith.science/pith/AKUB4K2ZUMQXQKMIW7WHZF3VR4.json","view_paper":"https://pith.science/paper/AKUB4K2Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.08604&json=true","fetch_graph":"https://pith.science/api/pith-number/AKUB4K2ZUMQXQKMIW7WHZF3VR4/graph.json","fetch_events":"https://pith.science/api/pith-number/AKUB4K2ZUMQXQKMIW7WHZF3VR4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AKUB4K2ZUMQXQKMIW7WHZF3VR4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AKUB4K2ZUMQXQKMIW7WHZF3VR4/action/storage_attestation","attest_author":"https://pith.science/pith/AKUB4K2ZUMQXQKMIW7WHZF3VR4/action/author_attestation","sign_citation":"https://pith.science/pith/AKUB4K2ZUMQXQKMIW7WHZF3VR4/action/citation_signature","submit_replication":"https://pith.science/pith/AKUB4K2ZUMQXQKMIW7WHZF3VR4/action/replication_record"}},"created_at":"2026-08-11T01:23:08.094805+00:00","updated_at":"2026-08-11T01:23:08.094805+00:00"}