{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NCHXKQIPBKKQ2MZVIMZFCJ3HLV","short_pith_number":"pith:NCHXKQIP","schema_version":"1.0","canonical_sha256":"688f75410f0a950d333543325127675d4f1d326dc435782cec945c873fdd2ab7","source":{"kind":"arxiv","id":"2604.13472","version":2},"attestation_state":"computed","paper":{"title":"Bridging MARL to SARL: An Order-Independent Multi-Agent Transformer via Latent Consensus","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"CMAT reformulates cooperative MARL as hierarchical SARL by generating a latent consensus vector that conditions simultaneous order-independent actions.","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.LG","authors_text":"Jing Gao, Sen Li, Zijian Zhao","submitted_at":"2026-04-15T04:52:22Z","abstract_excerpt":"Cooperative multi-agent reinforcement learning (MARL) is widely used to address large joint observation and action spaces by decomposing a centralized control problem into multiple interacting agents. However, such decomposition often introduces additional challenges, including non-stationarity, unstable training, weak coordination, and limited theoretical guarantees. In this paper, we propose the Consensus Multi-Agent Transformer (CMAT), a centralized framework that bridges cooperative MARL to a hierarchical single-agent reinforcement learning (SARL) formulation. CMAT treats all agents as a u"},"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":"2604.13472","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-04-15T04:52:22Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"ede4bd9ed23cdc642146b472fa104a9c54b8529a584bd2ea310cf860f85f3392","abstract_canon_sha256":"c8fe6206809e9d0592543acff461071f6376d3fa742d3f105575e1d51ebd96e5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T02:23:30.268544Z","signature_b64":"EJ2T/NoxThXXZaLUpbqCzqCx2EgcWNeBkVEvvUvtRYfwRdVtaYb0W1FnjNGv2b2JdPZ7LgrCSaJsQgmwEJ9XBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"688f75410f0a950d333543325127675d4f1d326dc435782cec945c873fdd2ab7","last_reissued_at":"2026-07-28T02:23:30.267577Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T02:23:30.267577Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bridging MARL to SARL: An Order-Independent Multi-Agent Transformer via Latent Consensus","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"CMAT reformulates cooperative MARL as hierarchical SARL by generating a latent consensus vector that conditions simultaneous order-independent actions.","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.LG","authors_text":"Jing Gao, Sen Li, Zijian Zhao","submitted_at":"2026-04-15T04:52:22Z","abstract_excerpt":"Cooperative multi-agent reinforcement learning (MARL) is widely used to address large joint observation and action spaces by decomposing a centralized control problem into multiple interacting agents. However, such decomposition often introduces additional challenges, including non-stationarity, unstable training, weak coordination, and limited theoretical guarantees. In this paper, we propose the Consensus Multi-Agent Transformer (CMAT), a centralized framework that bridges cooperative MARL to a hierarchical single-agent reinforcement learning (SARL) formulation. CMAT treats all agents as a u"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"CMAT bridges cooperative MARL to a hierarchical SARL formulation by autoregressively generating a high-level consensus vector that conditions simultaneous, order-independent action generation, allowing optimization with single-agent PPO while achieving superior performance on StarCraft II, Multi-Agent MuJoCo, and Google Research Football benchmarks.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The latent consensus vector produced by the transformer decoder actually captures sufficient coordination information to replace explicit agent-to-agent communication or centralized critics without loss of expressivity; this is assumed rather than proven and is only supported by empirical wins on the chosen benchmarks.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"CMAT uses a transformer decoder to produce a high-level consensus vector in latent space, enabling simultaneous order-independent actions by all agents and optimization via single-agent PPO, with superior results on StarCraft II, Multi-Agent MuJoCo, and Google Research Football.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"CMAT reformulates cooperative MARL as hierarchical SARL by generating a latent consensus vector that conditions simultaneous order-independent actions.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"32da2ca73a9024407380f65588279b58e41459d34d6de064af125d9e6a8d1187"},"source":{"id":"2604.13472","kind":"arxiv","version":2},"verdict":{"id":"8b1eb208-6b17-4a2e-815a-e7433c534e05","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T13:37:34.576192Z","strongest_claim":"CMAT bridges cooperative MARL to a hierarchical SARL formulation by autoregressively generating a high-level consensus vector that conditions simultaneous, order-independent action generation, allowing optimization with single-agent PPO while achieving superior performance on StarCraft II, Multi-Agent MuJoCo, and Google Research Football benchmarks.","one_line_summary":"CMAT uses a transformer decoder to produce a high-level consensus vector in latent space, enabling simultaneous order-independent actions by all agents and optimization via single-agent PPO, with superior results on StarCraft II, Multi-Agent MuJoCo, and Google Research Football.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The latent consensus vector produced by the transformer decoder actually captures sufficient coordination information to replace explicit agent-to-agent communication or centralized critics without loss of expressivity; this is assumed rather than proven and is only supported by empirical wins on the chosen benchmarks.","pith_extraction_headline":"CMAT reformulates cooperative MARL as hierarchical SARL by generating a latent consensus vector that conditions simultaneous order-independent actions."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.13472/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":"2604.13472","created_at":"2026-07-28T02:23:30.268035+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.13472v2","created_at":"2026-07-28T02:23:30.268035+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.13472","created_at":"2026-07-28T02:23:30.268035+00:00"},{"alias_kind":"pith_short_12","alias_value":"NCHXKQIPBKKQ","created_at":"2026-07-28T02:23:30.268035+00:00"},{"alias_kind":"pith_short_16","alias_value":"NCHXKQIPBKKQ2MZV","created_at":"2026-07-28T02:23:30.268035+00:00"},{"alias_kind":"pith_short_8","alias_value":"NCHXKQIP","created_at":"2026-07-28T02:23:30.268035+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/NCHXKQIPBKKQ2MZVIMZFCJ3HLV","json":"https://pith.science/pith/NCHXKQIPBKKQ2MZVIMZFCJ3HLV.json","graph_json":"https://pith.science/api/pith-number/NCHXKQIPBKKQ2MZVIMZFCJ3HLV/graph.json","events_json":"https://pith.science/api/pith-number/NCHXKQIPBKKQ2MZVIMZFCJ3HLV/events.json","paper":"https://pith.science/paper/NCHXKQIP"},"agent_actions":{"view_html":"https://pith.science/pith/NCHXKQIPBKKQ2MZVIMZFCJ3HLV","download_json":"https://pith.science/pith/NCHXKQIPBKKQ2MZVIMZFCJ3HLV.json","view_paper":"https://pith.science/paper/NCHXKQIP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.13472&json=true","fetch_graph":"https://pith.science/api/pith-number/NCHXKQIPBKKQ2MZVIMZFCJ3HLV/graph.json","fetch_events":"https://pith.science/api/pith-number/NCHXKQIPBKKQ2MZVIMZFCJ3HLV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NCHXKQIPBKKQ2MZVIMZFCJ3HLV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NCHXKQIPBKKQ2MZVIMZFCJ3HLV/action/storage_attestation","attest_author":"https://pith.science/pith/NCHXKQIPBKKQ2MZVIMZFCJ3HLV/action/author_attestation","sign_citation":"https://pith.science/pith/NCHXKQIPBKKQ2MZVIMZFCJ3HLV/action/citation_signature","submit_replication":"https://pith.science/pith/NCHXKQIPBKKQ2MZVIMZFCJ3HLV/action/replication_record"}},"created_at":"2026-07-28T02:23:30.268035+00:00","updated_at":"2026-07-28T02:23:30.268035+00:00"}