{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QLUR2MTAQI2N64OEVDQANKFXT5","short_pith_number":"pith:QLUR2MTA","schema_version":"1.0","canonical_sha256":"82e91d32608234df71c4a8e006a8b79f7c7de5279b0f323b4a5cfdd6b0f18c5b","source":{"kind":"arxiv","id":"2505.20671","version":1},"attestation_state":"computed","paper":{"title":"LLM-Guided Reinforcement Learning: Addressing Training Bottlenecks through Policy Modulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Heng Tan, Hua Yan, Yu Yang","submitted_at":"2025-05-27T03:40:02Z","abstract_excerpt":"While reinforcement learning (RL) has achieved notable success in various domains, training effective policies for complex tasks remains challenging. Agents often converge to local optima and fail to maximize long-term rewards. Existing approaches to mitigate training bottlenecks typically fall into two categories: (i) Automated policy refinement, which identifies critical states from past trajectories to guide policy updates, but suffers from costly and uncertain model training; and (ii) Human-in-the-loop refinement, where human feedback is used to correct agent behavior, but this does not sc"},"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":"2505.20671","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-27T03:40:02Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c06e14b40e1ba225cd6b9b1bac19230f43611b70544f396e51ea76720e5c7fc7","abstract_canon_sha256":"03165f2cc179ae988ade54af9f04582c2fd425043d318e6081c146f7737e1e9b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:16.317814Z","signature_b64":"f/qJlKHgHU5cTZDVYD/E3Vt6hPT85D/m543u5bYE5aszQcGX/ueuDuYBdTWfT8H8UGxKRjfuP7rzrSRalakTAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"82e91d32608234df71c4a8e006a8b79f7c7de5279b0f323b4a5cfdd6b0f18c5b","last_reissued_at":"2026-07-05T11:10:16.317345Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:16.317345Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLM-Guided Reinforcement Learning: Addressing Training Bottlenecks through Policy Modulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Heng Tan, Hua Yan, Yu Yang","submitted_at":"2025-05-27T03:40:02Z","abstract_excerpt":"While reinforcement learning (RL) has achieved notable success in various domains, training effective policies for complex tasks remains challenging. Agents often converge to local optima and fail to maximize long-term rewards. Existing approaches to mitigate training bottlenecks typically fall into two categories: (i) Automated policy refinement, which identifies critical states from past trajectories to guide policy updates, but suffers from costly and uncertain model training; and (ii) Human-in-the-loop refinement, where human feedback is used to correct agent behavior, but this does not sc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20671","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/2505.20671/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":"2505.20671","created_at":"2026-07-05T11:10:16.317409+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.20671v1","created_at":"2026-07-05T11:10:16.317409+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20671","created_at":"2026-07-05T11:10:16.317409+00:00"},{"alias_kind":"pith_short_12","alias_value":"QLUR2MTAQI2N","created_at":"2026-07-05T11:10:16.317409+00:00"},{"alias_kind":"pith_short_16","alias_value":"QLUR2MTAQI2N64OE","created_at":"2026-07-05T11:10:16.317409+00:00"},{"alias_kind":"pith_short_8","alias_value":"QLUR2MTA","created_at":"2026-07-05T11:10:16.317409+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/QLUR2MTAQI2N64OEVDQANKFXT5","json":"https://pith.science/pith/QLUR2MTAQI2N64OEVDQANKFXT5.json","graph_json":"https://pith.science/api/pith-number/QLUR2MTAQI2N64OEVDQANKFXT5/graph.json","events_json":"https://pith.science/api/pith-number/QLUR2MTAQI2N64OEVDQANKFXT5/events.json","paper":"https://pith.science/paper/QLUR2MTA"},"agent_actions":{"view_html":"https://pith.science/pith/QLUR2MTAQI2N64OEVDQANKFXT5","download_json":"https://pith.science/pith/QLUR2MTAQI2N64OEVDQANKFXT5.json","view_paper":"https://pith.science/paper/QLUR2MTA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.20671&json=true","fetch_graph":"https://pith.science/api/pith-number/QLUR2MTAQI2N64OEVDQANKFXT5/graph.json","fetch_events":"https://pith.science/api/pith-number/QLUR2MTAQI2N64OEVDQANKFXT5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QLUR2MTAQI2N64OEVDQANKFXT5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QLUR2MTAQI2N64OEVDQANKFXT5/action/storage_attestation","attest_author":"https://pith.science/pith/QLUR2MTAQI2N64OEVDQANKFXT5/action/author_attestation","sign_citation":"https://pith.science/pith/QLUR2MTAQI2N64OEVDQANKFXT5/action/citation_signature","submit_replication":"https://pith.science/pith/QLUR2MTAQI2N64OEVDQANKFXT5/action/replication_record"}},"created_at":"2026-07-05T11:10:16.317409+00:00","updated_at":"2026-07-05T11:10:16.317409+00:00"}