{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7EKWY7X6HB5CJEBEPYBKC44FOZ","short_pith_number":"pith:7EKWY7X6","schema_version":"1.0","canonical_sha256":"f9156c7efe387a2490247e02a17385766e41984f2f3200ab892c5a673beff7ac","source":{"kind":"arxiv","id":"2506.02522","version":1},"attestation_state":"computed","paper":{"title":"Think Twice, Act Once: A Co-Evolution Framework of LLM and RL for Large-Scale Decision Making","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chao Yang, Mingyang Sun, Wenyue Xu, Xu Wan","submitted_at":"2025-06-03T06:52:37Z","abstract_excerpt":"Recent advancements in Large Language Models (LLMs) and Reinforcement Learning (RL) have shown significant promise in decision-making tasks. Nevertheless, for large-scale industrial decision problems, both approaches face distinct challenges: LLMs lack real-time long-sequence decision-making capabilities, while RL struggles with sample efficiency in vast action spaces. To bridge this gap, we propose Agents Co-Evolution (ACE), a synergistic framework between LLMs and RL agents for large-scale decision-making scenarios. ACE introduces a dual-role trajectory refinement mechanism where LLMs act as"},"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":"2506.02522","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-03T06:52:37Z","cross_cats_sorted":[],"title_canon_sha256":"14bead213ecbadae0d55dcf18c920aa8cf9937366bc747e34ba0adc07f2c4abe","abstract_canon_sha256":"ec3e5f81ff9cb3c73e2e6bbbe7b88a3fd660a961bf60f29d43761e6f659235cf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:03.580259Z","signature_b64":"uoxuNUK1xlhsUPYOI7DuJOwS84ytiDz1A9hwPdsfodOw1iJhkuLsSq63JLe4fqnB714BLAX9yqXsqnUjl4/WCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f9156c7efe387a2490247e02a17385766e41984f2f3200ab892c5a673beff7ac","last_reissued_at":"2026-07-05T11:15:03.579695Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:03.579695Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Think Twice, Act Once: A Co-Evolution Framework of LLM and RL for Large-Scale Decision Making","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chao Yang, Mingyang Sun, Wenyue Xu, Xu Wan","submitted_at":"2025-06-03T06:52:37Z","abstract_excerpt":"Recent advancements in Large Language Models (LLMs) and Reinforcement Learning (RL) have shown significant promise in decision-making tasks. Nevertheless, for large-scale industrial decision problems, both approaches face distinct challenges: LLMs lack real-time long-sequence decision-making capabilities, while RL struggles with sample efficiency in vast action spaces. To bridge this gap, we propose Agents Co-Evolution (ACE), a synergistic framework between LLMs and RL agents for large-scale decision-making scenarios. ACE introduces a dual-role trajectory refinement mechanism where LLMs act as"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02522","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/2506.02522/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":"2506.02522","created_at":"2026-07-05T11:15:03.579758+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.02522v1","created_at":"2026-07-05T11:15:03.579758+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02522","created_at":"2026-07-05T11:15:03.579758+00:00"},{"alias_kind":"pith_short_12","alias_value":"7EKWY7X6HB5C","created_at":"2026-07-05T11:15:03.579758+00:00"},{"alias_kind":"pith_short_16","alias_value":"7EKWY7X6HB5CJEBE","created_at":"2026-07-05T11:15:03.579758+00:00"},{"alias_kind":"pith_short_8","alias_value":"7EKWY7X6","created_at":"2026-07-05T11:15:03.579758+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/7EKWY7X6HB5CJEBEPYBKC44FOZ","json":"https://pith.science/pith/7EKWY7X6HB5CJEBEPYBKC44FOZ.json","graph_json":"https://pith.science/api/pith-number/7EKWY7X6HB5CJEBEPYBKC44FOZ/graph.json","events_json":"https://pith.science/api/pith-number/7EKWY7X6HB5CJEBEPYBKC44FOZ/events.json","paper":"https://pith.science/paper/7EKWY7X6"},"agent_actions":{"view_html":"https://pith.science/pith/7EKWY7X6HB5CJEBEPYBKC44FOZ","download_json":"https://pith.science/pith/7EKWY7X6HB5CJEBEPYBKC44FOZ.json","view_paper":"https://pith.science/paper/7EKWY7X6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.02522&json=true","fetch_graph":"https://pith.science/api/pith-number/7EKWY7X6HB5CJEBEPYBKC44FOZ/graph.json","fetch_events":"https://pith.science/api/pith-number/7EKWY7X6HB5CJEBEPYBKC44FOZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7EKWY7X6HB5CJEBEPYBKC44FOZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7EKWY7X6HB5CJEBEPYBKC44FOZ/action/storage_attestation","attest_author":"https://pith.science/pith/7EKWY7X6HB5CJEBEPYBKC44FOZ/action/author_attestation","sign_citation":"https://pith.science/pith/7EKWY7X6HB5CJEBEPYBKC44FOZ/action/citation_signature","submit_replication":"https://pith.science/pith/7EKWY7X6HB5CJEBEPYBKC44FOZ/action/replication_record"}},"created_at":"2026-07-05T11:15:03.579758+00:00","updated_at":"2026-07-05T11:15:03.579758+00:00"}