{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:IVBQXHCCRWNVIZIE3JBCYYTXMI","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":"44eab2c241a2462ae8c64c0c47acad9d789f02461bc517ba48a40a039329fdb9","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-08-20T08:22:04Z","title_canon_sha256":"f936888df11caae452ae641c2e0024ba0a646c0b79227f55246e5d01d3afdd43"},"schema_version":"1.0","source":{"id":"2408.10635","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.10635","created_at":"2026-07-05T11:44:40Z"},{"alias_kind":"arxiv_version","alias_value":"2408.10635v3","created_at":"2026-07-05T11:44:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.10635","created_at":"2026-07-05T11:44:40Z"},{"alias_kind":"pith_short_12","alias_value":"IVBQXHCCRWNV","created_at":"2026-07-05T11:44:40Z"},{"alias_kind":"pith_short_16","alias_value":"IVBQXHCCRWNVIZIE","created_at":"2026-07-05T11:44:40Z"},{"alias_kind":"pith_short_8","alias_value":"IVBQXHCC","created_at":"2026-07-05T11:44:40Z"}],"graph_snapshots":[{"event_id":"sha256:fb8fe8206e38ed27d755ca071cec24259cdc231b7699f94dbc2b873896673cc0","target":"graph","created_at":"2026-07-05T11:44:40Z","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/2408.10635/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Traditional reinforcement learning and planning typically requires vast amounts of data and training to develop effective policies. In contrast, large language models (LLMs) exhibit strong generalization and zero-shot capabilities, but struggle with tasks that require detailed planning and decision-making in complex action spaces. We introduce STRATEGIST, a novel approach that integrates the strengths of both methods. Our approach leverages LLMs to search and update high-level strategies (as text), which are then refined and executed by low-level Monte Carlo Tree Search (MCTS). STRATEGIST is a","authors_text":"Guanzhi Wang, Jonathan Light, Min Cai, Wei Cheng, Weiqin Chen, Xiusi Chen, Yisong Yue, Ziniu Hu","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-08-20T08:22:04Z","title":"Strategist: Self-improvement of LLM Decision Making via Bi-Level Tree Search"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.10635","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":"sha256:813a4913ff09a673ed90a1bac71d1dfaabc5cb4d18e9df4bfd75b54fcf17aad5","target":"record","created_at":"2026-07-05T11:44:40Z","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":"44eab2c241a2462ae8c64c0c47acad9d789f02461bc517ba48a40a039329fdb9","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-08-20T08:22:04Z","title_canon_sha256":"f936888df11caae452ae641c2e0024ba0a646c0b79227f55246e5d01d3afdd43"},"schema_version":"1.0","source":{"id":"2408.10635","kind":"arxiv","version":3}},"canonical_sha256":"45430b9c428d9b546504da422c6277620d82e573af60196009e3a125cb7feec1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"45430b9c428d9b546504da422c6277620d82e573af60196009e3a125cb7feec1","first_computed_at":"2026-07-05T11:44:40.463265Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:44:40.463265Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dcaHYt0IJd6tfG8dDQA2DeK9TI9/tup0eW7y6CYyCAysxM9yvVxX+ujRDsMI/T720O4yxtmmaTdZmvsHPczqDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:44:40.463720Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.10635","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:813a4913ff09a673ed90a1bac71d1dfaabc5cb4d18e9df4bfd75b54fcf17aad5","sha256:fb8fe8206e38ed27d755ca071cec24259cdc231b7699f94dbc2b873896673cc0"],"state_sha256":"f84e877bc4c13a8029b4d739a65e753aaf20d396c7a678fb26bd8bc72f399da4"}