{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:PNBZHVVNWGFAZVLHMX2TN3C5QG","short_pith_number":"pith:PNBZHVVN","canonical_record":{"source":{"id":"2404.00282","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-30T08:28:08Z","cross_cats_sorted":["cs.AI","cs.CL","cs.RO"],"title_canon_sha256":"9f5a8b74cae0278b07d250d6ec1df6cc1d5e35529cf6902ceb31e63904fa784b","abstract_canon_sha256":"c698c58b3da6aba5b94b2f780209d83a9979e6ac9df3a74bb0821c717c0c974b"},"schema_version":"1.0"},"canonical_sha256":"7b4393d6adb18a0cd56765f536ec5d81a115faeb052349b352cd61e4e73ec29b","source":{"kind":"arxiv","id":"2404.00282","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.00282","created_at":"2026-07-05T09:37:52Z"},{"alias_kind":"arxiv_version","alias_value":"2404.00282v3","created_at":"2026-07-05T09:37:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.00282","created_at":"2026-07-05T09:37:52Z"},{"alias_kind":"pith_short_12","alias_value":"PNBZHVVNWGFA","created_at":"2026-07-05T09:37:52Z"},{"alias_kind":"pith_short_16","alias_value":"PNBZHVVNWGFAZVLH","created_at":"2026-07-05T09:37:52Z"},{"alias_kind":"pith_short_8","alias_value":"PNBZHVVN","created_at":"2026-07-05T09:37:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:PNBZHVVNWGFAZVLHMX2TN3C5QG","target":"record","payload":{"canonical_record":{"source":{"id":"2404.00282","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-30T08:28:08Z","cross_cats_sorted":["cs.AI","cs.CL","cs.RO"],"title_canon_sha256":"9f5a8b74cae0278b07d250d6ec1df6cc1d5e35529cf6902ceb31e63904fa784b","abstract_canon_sha256":"c698c58b3da6aba5b94b2f780209d83a9979e6ac9df3a74bb0821c717c0c974b"},"schema_version":"1.0"},"canonical_sha256":"7b4393d6adb18a0cd56765f536ec5d81a115faeb052349b352cd61e4e73ec29b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:37:52.652186Z","signature_b64":"ts3XzGdbqoe2p+PP4xprNbYKrjWpUVqrnJa+UJdNgm2CyqvQhqLA3VoLvWMxuCTzI2wSVJOeZ66QnStJW+twDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b4393d6adb18a0cd56765f536ec5d81a115faeb052349b352cd61e4e73ec29b","last_reissued_at":"2026-07-05T09:37:52.651656Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:37:52.651656Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.00282","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:37:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fvP3HMJeCGQdbbsS528P/9eXYI8djHa4qwFGlMdwTxMF0FAiZJCI4I3V6hwNDMYlKJf4SXkukADaB2Z6SAqhCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T20:58:08.530499Z"},"content_sha256":"27c10281b927ee8939eaa505ebdf6c5ab09e3f20a6ec2eed7fe3255b8ecbcf28","schema_version":"1.0","event_id":"sha256:27c10281b927ee8939eaa505ebdf6c5ab09e3f20a6ec2eed7fe3255b8ecbcf28"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:PNBZHVVNWGFAZVLHMX2TN3C5QG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Survey on Large Language Model-Enhanced Reinforcement Learning: Concept, Taxonomy, and Methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.RO"],"primary_cat":"cs.LG","authors_text":"Gaoqi Liang, Guolong Liu, Huan Zhao, Jinyue Yan, Junhua Zhao, Ting Shu, Yue Chen, Yuheng Cheng, Yuji Cao, Yun Li","submitted_at":"2024-03-30T08:28:08Z","abstract_excerpt":"With extensive pre-trained knowledge and high-level general capabilities, large language models (LLMs) emerge as a promising avenue to augment reinforcement learning (RL) in aspects such as multi-task learning, sample efficiency, and high-level task planning. In this survey, we provide a comprehensive review of the existing literature in LLM-enhanced RL and summarize its characteristics compared to conventional RL methods, aiming to clarify the research scope and directions for future studies. Utilizing the classical agent-environment interaction paradigm, we propose a structured taxonomy to s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.00282","kind":"arxiv","version":3},"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/2404.00282/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:37:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RtvPc9A5cC2YASAUmHebk6hmO71TkClPejTswDmUUqVaseSX7gbJVqXRjEaGzNJz7NPE6fBlq23FUcn/oycRDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T20:58:08.531050Z"},"content_sha256":"76d43a1cc6d337ba09e469efecb7ed10c217519798bae4e21e4916a190830a3d","schema_version":"1.0","event_id":"sha256:76d43a1cc6d337ba09e469efecb7ed10c217519798bae4e21e4916a190830a3d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PNBZHVVNWGFAZVLHMX2TN3C5QG/bundle.json","state_url":"https://pith.science/pith/PNBZHVVNWGFAZVLHMX2TN3C5QG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PNBZHVVNWGFAZVLHMX2TN3C5QG/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T20:58:08Z","links":{"resolver":"https://pith.science/pith/PNBZHVVNWGFAZVLHMX2TN3C5QG","bundle":"https://pith.science/pith/PNBZHVVNWGFAZVLHMX2TN3C5QG/bundle.json","state":"https://pith.science/pith/PNBZHVVNWGFAZVLHMX2TN3C5QG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PNBZHVVNWGFAZVLHMX2TN3C5QG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PNBZHVVNWGFAZVLHMX2TN3C5QG","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":"c698c58b3da6aba5b94b2f780209d83a9979e6ac9df3a74bb0821c717c0c974b","cross_cats_sorted":["cs.AI","cs.CL","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-30T08:28:08Z","title_canon_sha256":"9f5a8b74cae0278b07d250d6ec1df6cc1d5e35529cf6902ceb31e63904fa784b"},"schema_version":"1.0","source":{"id":"2404.00282","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.00282","created_at":"2026-07-05T09:37:52Z"},{"alias_kind":"arxiv_version","alias_value":"2404.00282v3","created_at":"2026-07-05T09:37:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.00282","created_at":"2026-07-05T09:37:52Z"},{"alias_kind":"pith_short_12","alias_value":"PNBZHVVNWGFA","created_at":"2026-07-05T09:37:52Z"},{"alias_kind":"pith_short_16","alias_value":"PNBZHVVNWGFAZVLH","created_at":"2026-07-05T09:37:52Z"},{"alias_kind":"pith_short_8","alias_value":"PNBZHVVN","created_at":"2026-07-05T09:37:52Z"}],"graph_snapshots":[{"event_id":"sha256:76d43a1cc6d337ba09e469efecb7ed10c217519798bae4e21e4916a190830a3d","target":"graph","created_at":"2026-07-05T09:37:52Z","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/2404.00282/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With extensive pre-trained knowledge and high-level general capabilities, large language models (LLMs) emerge as a promising avenue to augment reinforcement learning (RL) in aspects such as multi-task learning, sample efficiency, and high-level task planning. In this survey, we provide a comprehensive review of the existing literature in LLM-enhanced RL and summarize its characteristics compared to conventional RL methods, aiming to clarify the research scope and directions for future studies. Utilizing the classical agent-environment interaction paradigm, we propose a structured taxonomy to s","authors_text":"Gaoqi Liang, Guolong Liu, Huan Zhao, Jinyue Yan, Junhua Zhao, Ting Shu, Yue Chen, Yuheng Cheng, Yuji Cao, Yun Li","cross_cats":["cs.AI","cs.CL","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-30T08:28:08Z","title":"Survey on Large Language Model-Enhanced Reinforcement Learning: Concept, Taxonomy, and Methods"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.00282","kind":"arxiv","version":3},"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":"sha256:27c10281b927ee8939eaa505ebdf6c5ab09e3f20a6ec2eed7fe3255b8ecbcf28","target":"record","created_at":"2026-07-05T09:37:52Z","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":"c698c58b3da6aba5b94b2f780209d83a9979e6ac9df3a74bb0821c717c0c974b","cross_cats_sorted":["cs.AI","cs.CL","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-30T08:28:08Z","title_canon_sha256":"9f5a8b74cae0278b07d250d6ec1df6cc1d5e35529cf6902ceb31e63904fa784b"},"schema_version":"1.0","source":{"id":"2404.00282","kind":"arxiv","version":3}},"canonical_sha256":"7b4393d6adb18a0cd56765f536ec5d81a115faeb052349b352cd61e4e73ec29b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7b4393d6adb18a0cd56765f536ec5d81a115faeb052349b352cd61e4e73ec29b","first_computed_at":"2026-07-05T09:37:52.651656Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:37:52.651656Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ts3XzGdbqoe2p+PP4xprNbYKrjWpUVqrnJa+UJdNgm2CyqvQhqLA3VoLvWMxuCTzI2wSVJOeZ66QnStJW+twDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:37:52.652186Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.00282","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:27c10281b927ee8939eaa505ebdf6c5ab09e3f20a6ec2eed7fe3255b8ecbcf28","sha256:76d43a1cc6d337ba09e469efecb7ed10c217519798bae4e21e4916a190830a3d"],"state_sha256":"bd6878a189eac1cc28b33fb8777b76f221a3546cd61f221b3525eeaa6bdc5cfa"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tguh3eN/R4fdMw68ogcsSerT9sbofmkmvYBfk/LoJntMOfD7GMFXtPIdzOC+HqHU/EQXYYLoc0rtmj2cc0f/Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T20:58:08.536892Z","bundle_sha256":"13c79cadfeaf052887e7144e5ff594047ef37906b5b8b8e955346dbff205a633"}}