{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:67QAZYTLYFO4IHPCAM7O6GTLQR","short_pith_number":"pith:67QAZYTL","schema_version":"1.0","canonical_sha256":"f7e00ce26bc15dc41de2033eef1a6b84606aafbdd1795ac2207aaa6fed6c368d","source":{"kind":"arxiv","id":"2405.11106","version":1},"attestation_state":"computed","paper":{"title":"LLM-based Multi-Agent Reinforcement Learning: Current and Future Directions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG","cs.RO"],"primary_cat":"cs.MA","authors_text":"Chuanneng Sun, Dario Pompili, Songjun Huang","submitted_at":"2024-05-17T22:10:23Z","abstract_excerpt":"In recent years, Large Language Models (LLMs) have shown great abilities in various tasks, including question answering, arithmetic problem solving, and poem writing, among others. Although research on LLM-as-an-agent has shown that LLM can be applied to Reinforcement Learning (RL) and achieve decent results, the extension of LLM-based RL to Multi-Agent System (MAS) is not trivial, as many aspects, such as coordination and communication between agents, are not considered in the RL frameworks of a single agent. To inspire more research on LLM-based MARL, in this letter, we survey the existing L"},"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":"2405.11106","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2024-05-17T22:10:23Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.RO"],"title_canon_sha256":"14a08e83ebd015ca8887524552e33edd13efd7776f2bc1ad39b1f2fada2a7aae","abstract_canon_sha256":"6d4e1d5182e7c91c2d140a5c8fd45155689266ed2fd2ebf66e305973f1bfd117"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:20:33.383554Z","signature_b64":"MYgofDW07HZ3BeQNT9hsjlHmS6C1wlvffrPx7IRqLc4z9fVR5e1kIHjnnXgEu5xUAb4+ig9/Prdl1/HWqjmABg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f7e00ce26bc15dc41de2033eef1a6b84606aafbdd1795ac2207aaa6fed6c368d","last_reissued_at":"2026-07-05T08:20:33.383136Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:20:33.383136Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLM-based Multi-Agent Reinforcement Learning: Current and Future Directions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG","cs.RO"],"primary_cat":"cs.MA","authors_text":"Chuanneng Sun, Dario Pompili, Songjun Huang","submitted_at":"2024-05-17T22:10:23Z","abstract_excerpt":"In recent years, Large Language Models (LLMs) have shown great abilities in various tasks, including question answering, arithmetic problem solving, and poem writing, among others. Although research on LLM-as-an-agent has shown that LLM can be applied to Reinforcement Learning (RL) and achieve decent results, the extension of LLM-based RL to Multi-Agent System (MAS) is not trivial, as many aspects, such as coordination and communication between agents, are not considered in the RL frameworks of a single agent. To inspire more research on LLM-based MARL, in this letter, we survey the existing L"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.11106","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/2405.11106/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":"2405.11106","created_at":"2026-07-05T08:20:33.383185+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.11106v1","created_at":"2026-07-05T08:20:33.383185+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.11106","created_at":"2026-07-05T08:20:33.383185+00:00"},{"alias_kind":"pith_short_12","alias_value":"67QAZYTLYFO4","created_at":"2026-07-05T08:20:33.383185+00:00"},{"alias_kind":"pith_short_16","alias_value":"67QAZYTLYFO4IHPC","created_at":"2026-07-05T08:20:33.383185+00:00"},{"alias_kind":"pith_short_8","alias_value":"67QAZYTL","created_at":"2026-07-05T08:20:33.383185+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":14,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19920","citing_title":"Deep-Unfolded Coordination","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12655","citing_title":"Robust Instruction Compliance in Cooperative Multi-Agent Reinforcement Learning","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25746","citing_title":"Multi-Agent Coordination Adaptation via Structure-Guided Orchestration","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18799","citing_title":"ReCrit: Transition-Aware Reinforcement Learning for Scientific Critic Reasoning","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2411.18279","citing_title":"Large Language Model-Brained GUI Agents: A Survey","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2510.14063","citing_title":"Adaptive Obstacle-Aware Task Assignment and Planning for Heterogeneous Robot Teaming","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2507.02592","citing_title":"WebSailor: Navigating Super-human Reasoning for Web Agent","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2601.01885","citing_title":"Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model Agents","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2603.12631","citing_title":"Joint Optimization of Multi-agent Memory System","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2507.21046","citing_title":"A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence","ref_index":125,"is_internal_anchor":false},{"citing_arxiv_id":"2501.06322","citing_title":"Multi-Agent Collaboration Mechanisms: A Survey of LLMs","ref_index":118,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18133","citing_title":"Multi-Agent Systems: From Classical Paradigms to Large Foundation Model-Enabled Futures","ref_index":131,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15840","citing_title":"CoEvolve: Training LLM Agents via Agent-Data Mutual Evolution","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17191","citing_title":"Do LLM-derived graph priors improve multi-agent coordination?","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/67QAZYTLYFO4IHPCAM7O6GTLQR","json":"https://pith.science/pith/67QAZYTLYFO4IHPCAM7O6GTLQR.json","graph_json":"https://pith.science/api/pith-number/67QAZYTLYFO4IHPCAM7O6GTLQR/graph.json","events_json":"https://pith.science/api/pith-number/67QAZYTLYFO4IHPCAM7O6GTLQR/events.json","paper":"https://pith.science/paper/67QAZYTL"},"agent_actions":{"view_html":"https://pith.science/pith/67QAZYTLYFO4IHPCAM7O6GTLQR","download_json":"https://pith.science/pith/67QAZYTLYFO4IHPCAM7O6GTLQR.json","view_paper":"https://pith.science/paper/67QAZYTL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.11106&json=true","fetch_graph":"https://pith.science/api/pith-number/67QAZYTLYFO4IHPCAM7O6GTLQR/graph.json","fetch_events":"https://pith.science/api/pith-number/67QAZYTLYFO4IHPCAM7O6GTLQR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/67QAZYTLYFO4IHPCAM7O6GTLQR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/67QAZYTLYFO4IHPCAM7O6GTLQR/action/storage_attestation","attest_author":"https://pith.science/pith/67QAZYTLYFO4IHPCAM7O6GTLQR/action/author_attestation","sign_citation":"https://pith.science/pith/67QAZYTLYFO4IHPCAM7O6GTLQR/action/citation_signature","submit_replication":"https://pith.science/pith/67QAZYTLYFO4IHPCAM7O6GTLQR/action/replication_record"}},"created_at":"2026-07-05T08:20:33.383185+00:00","updated_at":"2026-07-05T08:20:33.383185+00:00"}