{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:7EKWY7X6HB5CJEBEPYBKC44FOZ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"ec3e5f81ff9cb3c73e2e6bbbe7b88a3fd660a961bf60f29d43761e6f659235cf","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-03T06:52:37Z","title_canon_sha256":"14bead213ecbadae0d55dcf18c920aa8cf9937366bc747e34ba0adc07f2c4abe"},"schema_version":"1.0","source":{"id":"2506.02522","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.02522","created_at":"2026-07-05T11:15:03Z"},{"alias_kind":"arxiv_version","alias_value":"2506.02522v1","created_at":"2026-07-05T11:15:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02522","created_at":"2026-07-05T11:15:03Z"},{"alias_kind":"pith_short_12","alias_value":"7EKWY7X6HB5C","created_at":"2026-07-05T11:15:03Z"},{"alias_kind":"pith_short_16","alias_value":"7EKWY7X6HB5CJEBE","created_at":"2026-07-05T11:15:03Z"},{"alias_kind":"pith_short_8","alias_value":"7EKWY7X6","created_at":"2026-07-05T11:15:03Z"}],"graph_snapshots":[{"event_id":"sha256:0979457779b23c753ac5d29bc64007875427b73957882bf185d2b425db38d0dc","target":"graph","created_at":"2026-07-05T11:15:03Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2506.02522/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chao Yang, Mingyang Sun, Wenyue Xu, Xu Wan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-03T06:52:37Z","title":"Think Twice, Act Once: A Co-Evolution Framework of LLM and RL for Large-Scale Decision Making"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02522","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:dfb4d251f7fa3192367c305545d0a1391f0324f111a63649fd1f90c0bccbd640","target":"record","created_at":"2026-07-05T11:15:03Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"ec3e5f81ff9cb3c73e2e6bbbe7b88a3fd660a961bf60f29d43761e6f659235cf","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-03T06:52:37Z","title_canon_sha256":"14bead213ecbadae0d55dcf18c920aa8cf9937366bc747e34ba0adc07f2c4abe"},"schema_version":"1.0","source":{"id":"2506.02522","kind":"arxiv","version":1}},"canonical_sha256":"f9156c7efe387a2490247e02a17385766e41984f2f3200ab892c5a673beff7ac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f9156c7efe387a2490247e02a17385766e41984f2f3200ab892c5a673beff7ac","first_computed_at":"2026-07-05T11:15:03.579695Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:15:03.579695Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uoxuNUK1xlhsUPYOI7DuJOwS84ytiDz1A9hwPdsfodOw1iJhkuLsSq63JLe4fqnB714BLAX9yqXsqnUjl4/WCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:15:03.580259Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.02522","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dfb4d251f7fa3192367c305545d0a1391f0324f111a63649fd1f90c0bccbd640","sha256:0979457779b23c753ac5d29bc64007875427b73957882bf185d2b425db38d0dc"],"state_sha256":"b208bb922b07dcc785225a9af0aa7eb162a73bc00ebcd55f64cfed0672dada0f"}