{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EJDO5PHPUCMTTI64X2S2AY2EJM","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":"886ff5390facb70dea5dd9c961f245da0b8a5c08ebf1d2ba11f1ea7d8c7c71ca","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-02-29T16:07:22Z","title_canon_sha256":"67395c5d87f8a38d1a84fd46d4c669b29cc06e74f8585993a743263821a5f145"},"schema_version":"1.0","source":{"id":"2402.19299","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.19299","created_at":"2026-07-05T07:50:43Z"},{"alias_kind":"arxiv_version","alias_value":"2402.19299v1","created_at":"2026-07-05T07:50:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.19299","created_at":"2026-07-05T07:50:43Z"},{"alias_kind":"pith_short_12","alias_value":"EJDO5PHPUCMT","created_at":"2026-07-05T07:50:43Z"},{"alias_kind":"pith_short_16","alias_value":"EJDO5PHPUCMTTI64","created_at":"2026-07-05T07:50:43Z"},{"alias_kind":"pith_short_8","alias_value":"EJDO5PHP","created_at":"2026-07-05T07:50:43Z"}],"graph_snapshots":[{"event_id":"sha256:bea1dc8b11d781760d8e100b565ba412e882ea493f66c42db92ec4d4e3a391fb","target":"graph","created_at":"2026-07-05T07:50:43Z","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/2402.19299/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have demonstrated proficiency in utilizing various tools by coding, yet they face limitations in handling intricate logic and precise control. In embodied tasks, high-level planning is amenable to direct coding, while low-level actions often necessitate task-specific refinement, such as Reinforcement Learning (RL). To seamlessly integrate both modalities, we introduce a two-level hierarchical framework, RL-GPT, comprising a slow agent and a fast agent. The slow agent analyzes actions suitable for coding, while the fast agent executes coding tasks. This decompositio","authors_text":"Haoqi Yuan, Jiaya Jia, Minda Hu, Shaoteng Liu, Shu Liu, Yanwei Li, Yukang Chen, Zongqing Lu","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-02-29T16:07:22Z","title":"RL-GPT: Integrating Reinforcement Learning and Code-as-policy"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.19299","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":"sha256:59a44fa8c90804f536e76d4dfc3525e877cdbe22f6c0031666fa12898f3fa5a2","target":"record","created_at":"2026-07-05T07:50:43Z","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":"886ff5390facb70dea5dd9c961f245da0b8a5c08ebf1d2ba11f1ea7d8c7c71ca","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-02-29T16:07:22Z","title_canon_sha256":"67395c5d87f8a38d1a84fd46d4c669b29cc06e74f8585993a743263821a5f145"},"schema_version":"1.0","source":{"id":"2402.19299","kind":"arxiv","version":1}},"canonical_sha256":"2246eebcefa09939a3dcbea5a063444b0147d2020a79001899c501447dad358a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2246eebcefa09939a3dcbea5a063444b0147d2020a79001899c501447dad358a","first_computed_at":"2026-07-05T07:50:43.612913Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:50:43.612913Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jHq1SPTZ5RjzlgZ6MCugdCFMb8Uw2bNmy547A383LSQu3QHht/51NTnNI5tMTD5aFnpcaXAESkKhQxafwbcIBA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:50:43.613426Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.19299","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:59a44fa8c90804f536e76d4dfc3525e877cdbe22f6c0031666fa12898f3fa5a2","sha256:bea1dc8b11d781760d8e100b565ba412e882ea493f66c42db92ec4d4e3a391fb"],"state_sha256":"e792aa7c943ff2fecf4464876f160a8bb974ccdd47fe341fef912f99c1f74fe6"}