{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:KQRAAU7LVMMXOKM7446XBDC42V","short_pith_number":"pith:KQRAAU7L","schema_version":"1.0","canonical_sha256":"54220053ebab1977299fe73d708c5cd54b37022e9760061182be87743661d9f1","source":{"kind":"arxiv","id":"2310.04406","version":3},"attestation_state":"computed","paper":{"title":"Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Language models use Monte Carlo tree search with self-reflections to plan and act as agents.","cross_cats":["cs.CL","cs.CV","cs.LG"],"primary_cat":"cs.AI","authors_text":"Andy Zhou, Haohan Wang, Kai Yan, Michal Shlapentokh-Rothman, Yu-Xiong Wang","submitted_at":"2023-10-06T17:55:11Z","abstract_excerpt":"While language models (LMs) have shown potential across a range of decision-making tasks, their reliance on simple acting processes limits their broad deployment as autonomous agents. In this paper, we introduce Language Agent Tree Search (LATS) -- the first general framework that synergizes the capabilities of LMs in reasoning, acting, and planning. By leveraging the in-context learning ability of LMs, we integrate Monte Carlo Tree Search into LATS to enable LMs as agents, along with LM-powered value functions and self-reflections for proficient exploration and enhanced decision-making. A key"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2310.04406","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-10-06T17:55:11Z","cross_cats_sorted":["cs.CL","cs.CV","cs.LG"],"title_canon_sha256":"32f9679ff79944b542b9890ca1a452e4bbd2842c0b4f8062941fda58f1d86326","abstract_canon_sha256":"f2175a07ca90456aaed3ab5aa5f7ed2f45abc1456dee4d6c1f7af366abc59403"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:46.239689Z","signature_b64":"RuNGnTwh0RxMzHSlbkpImf9jPuoc2dTCaNrOeGWCnHLfyVTcFSiYyn/MyFwKA9F9QOsiIr9US74HS0J0f0zbAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"54220053ebab1977299fe73d708c5cd54b37022e9760061182be87743661d9f1","last_reissued_at":"2026-05-17T23:38:46.239259Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:46.239259Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Language models use Monte Carlo tree search with self-reflections to plan and act as agents.","cross_cats":["cs.CL","cs.CV","cs.LG"],"primary_cat":"cs.AI","authors_text":"Andy Zhou, Haohan Wang, Kai Yan, Michal Shlapentokh-Rothman, Yu-Xiong Wang","submitted_at":"2023-10-06T17:55:11Z","abstract_excerpt":"While language models (LMs) have shown potential across a range of decision-making tasks, their reliance on simple acting processes limits their broad deployment as autonomous agents. In this paper, we introduce Language Agent Tree Search (LATS) -- the first general framework that synergizes the capabilities of LMs in reasoning, acting, and planning. By leveraging the in-context learning ability of LMs, we integrate Monte Carlo Tree Search into LATS to enable LMs as agents, along with LM-powered value functions and self-reflections for proficient exploration and enhanced decision-making. A key"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"LATS achieves state-of-the-art pass@1 accuracy (92.7%) for programming on HumanEval with GPT-4 and demonstrates gradient-free performance (average score of 75.9) comparable to gradient-based fine-tuning for web navigation on WebShop with GPT-3.5.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That language models can reliably serve as value functions and self-reflectors within Monte Carlo Tree Search using only in-context learning and external environment feedback, without needing task-specific training.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"LATS integrates Monte Carlo Tree Search with language models using in-context learning, value functions, and self-reflection to achieve 92.7% pass@1 on HumanEval and competitive web navigation performance.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Language models use Monte Carlo tree search with self-reflections to plan and act as agents.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"5892c298ba859d75ea61aa2dc47d8bb6d764df8491c2e8ee9aa0a1a23f3a91a9"},"source":{"id":"2310.04406","kind":"arxiv","version":3},"verdict":{"id":"58a4c1bb-024c-4319-b169-45e58f2a7e48","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T23:21:58.759085Z","strongest_claim":"LATS achieves state-of-the-art pass@1 accuracy (92.7%) for programming on HumanEval with GPT-4 and demonstrates gradient-free performance (average score of 75.9) comparable to gradient-based fine-tuning for web navigation on WebShop with GPT-3.5.","one_line_summary":"LATS integrates Monte Carlo Tree Search with language models using in-context learning, value functions, and self-reflection to achieve 92.7% pass@1 on HumanEval and competitive web navigation performance.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That language models can reliably serve as value functions and self-reflectors within Monte Carlo Tree Search using only in-context learning and external environment feedback, without needing task-specific training.","pith_extraction_headline":"Language models use Monte Carlo tree search with self-reflections to plan and act as agents."},"references":{"count":13,"sample":[{"doi":"","year":null,"title":"Graph of thoughts: Solving elaborate problems with large language models","work_id":"34ed66c5-13ac-4799-b958-8e57d3de4705","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Evaluating Large Language Models Trained on Code","work_id":"042493e9-b26f-4b4e-bbde-382072ca9b08","ref_index":2,"cited_arxiv_id":"2107.03374","is_internal_anchor":true},{"doi":"","year":null,"title":"Training Verifiers to Solve Math Word Problems","work_id":"acab1aa8-b4d6-40e0-a3ee-25341701dca2","ref_index":3,"cited_arxiv_id":"2110.14168","is_internal_anchor":true},{"doi":"","year":null,"title":"Mastering Diverse Domains through World Models","work_id":"6aeb260f-8c7c-4f9c-b98b-067cd7c59acd","ref_index":4,"cited_arxiv_id":"2301.04104","is_internal_anchor":true},{"doi":"","year":null,"title":"Reason for fu- ture, act for now: A principled framework for au- tonomous LLM agents with provable sample efficiency","work_id":"ba51c107-b4c4-45ab-a1ae-5164af8a0587","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":13,"snapshot_sha256":"b9d8f897f7b090517e4fe11ad6f64a7325bfeeedb790d403733f144fd63baf18","internal_anchors":7},"formal_canon":{"evidence_count":2,"snapshot_sha256":"9e8bc7682508675408b709a73a7f8b476de14435e933a514458a54ed2e236fc0"},"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":"2310.04406","created_at":"2026-05-17T23:38:46.239323+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.04406v3","created_at":"2026-05-17T23:38:46.239323+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.04406","created_at":"2026-05-17T23:38:46.239323+00:00"},{"alias_kind":"pith_short_12","alias_value":"KQRAAU7LVMMX","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"KQRAAU7LVMMXOKM7","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"KQRAAU7L","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":31,"internal_anchor_count":31,"sample":[{"citing_arxiv_id":"2504.01990","citing_title":"Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems","ref_index":215,"is_internal_anchor":true},{"citing_arxiv_id":"2505.11737","citing_title":"TokUR: Token-Level Uncertainty Estimation for Large Language Model Reasoning","ref_index":47,"is_internal_anchor":true},{"citing_arxiv_id":"2605.22566","citing_title":"GraphFlow: A Graph-Based Workflow Management for Efficient LLM-Agent Serving","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2605.22138","citing_title":"Efficient Agentic Reasoning Through Self-Regulated Simulative Planning","ref_index":127,"is_internal_anchor":true},{"citing_arxiv_id":"2605.22106","citing_title":"ArborKV: Structure-Aware KV Cache Management for Scaling Tree-based LLM Reasoning","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21516","citing_title":"Harnesses for Inference-Time Alignment over Execution Trajectories","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2310.02170","citing_title":"A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration","ref_index":31,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09730","citing_title":"RubricRefine: Improving Tool-Use Agent Reliability with Training-Free Pre-Execution Refinement","ref_index":51,"is_internal_anchor":true},{"citing_arxiv_id":"2510.08804","citing_title":"MOSAIC: Multi-agent Orchestration for Task-Intelligent Scientific Coding","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2510.14703","citing_title":"ToolPRM: Fine-Grained Inference Scaling of Structured Outputs for Function Calling","ref_index":58,"is_internal_anchor":true},{"citing_arxiv_id":"2511.00739","citing_title":"Towards Understanding, Analyzing, and Optimizing Agentic AI Execution: A CPU-Centric Perspective","ref_index":44,"is_internal_anchor":true},{"citing_arxiv_id":"2404.11584","citing_title":"The Landscape of Emerging AI Agent Architectures for Reasoning, Planning, and Tool Calling: A Survey","ref_index":40,"is_internal_anchor":true},{"citing_arxiv_id":"2512.18470","citing_title":"SWE-EVO: Benchmarking Coding Agents in Long-Horizon Software Evolution Scenarios","ref_index":68,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11853","citing_title":"GEAR: Granularity-Adaptive Advantage Reweighting for LLM Agents via Self-Distillation","ref_index":34,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09730","citing_title":"RubricRefine: Improving Tool-Use Agent Reliability with Training-Free Pre-Execution Refinement","ref_index":52,"is_internal_anchor":true},{"citing_arxiv_id":"2504.19678","citing_title":"From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review","ref_index":39,"is_internal_anchor":true},{"citing_arxiv_id":"2602.20867","citing_title":"SoK: Agentic Skills -- Beyond Tool Use in LLM Agents","ref_index":54,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12755","citing_title":"State-Centric Decision Process","ref_index":62,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13625","citing_title":"How to Interpret Agent Behavior","ref_index":63,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11853","citing_title":"GEAR: Granularity-Adaptive Advantage Reweighting for LLM Agents via Self-Distillation","ref_index":34,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12087","citing_title":"Intermediate Artifacts as First-Class Citizens: A Data Model for Durable Intermediate Artifacts in Agentic Systems","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2310.11511","citing_title":"Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection","ref_index":57,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10913","citing_title":"Shepherd: A Runtime Substrate Empowering Meta-Agents with a Formalized Execution Trace","ref_index":58,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09730","citing_title":"RubricRefine: Improving Tool-Use Agent Reliability with Training-Free Pre-Execution Refinement","ref_index":50,"is_internal_anchor":true},{"citing_arxiv_id":"2605.03356","citing_title":"POSTCONDBENCH: Benchmarking Correctness and Completeness in Formal Postcondition Inference","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KQRAAU7LVMMXOKM7446XBDC42V","json":"https://pith.science/pith/KQRAAU7LVMMXOKM7446XBDC42V.json","graph_json":"https://pith.science/api/pith-number/KQRAAU7LVMMXOKM7446XBDC42V/graph.json","events_json":"https://pith.science/api/pith-number/KQRAAU7LVMMXOKM7446XBDC42V/events.json","paper":"https://pith.science/paper/KQRAAU7L"},"agent_actions":{"view_html":"https://pith.science/pith/KQRAAU7LVMMXOKM7446XBDC42V","download_json":"https://pith.science/pith/KQRAAU7LVMMXOKM7446XBDC42V.json","view_paper":"https://pith.science/paper/KQRAAU7L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.04406&json=true","fetch_graph":"https://pith.science/api/pith-number/KQRAAU7LVMMXOKM7446XBDC42V/graph.json","fetch_events":"https://pith.science/api/pith-number/KQRAAU7LVMMXOKM7446XBDC42V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KQRAAU7LVMMXOKM7446XBDC42V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KQRAAU7LVMMXOKM7446XBDC42V/action/storage_attestation","attest_author":"https://pith.science/pith/KQRAAU7LVMMXOKM7446XBDC42V/action/author_attestation","sign_citation":"https://pith.science/pith/KQRAAU7LVMMXOKM7446XBDC42V/action/citation_signature","submit_replication":"https://pith.science/pith/KQRAAU7LVMMXOKM7446XBDC42V/action/replication_record"}},"created_at":"2026-05-17T23:38:46.239323+00:00","updated_at":"2026-05-17T23:38:46.239323+00:00"}