{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:KQRAAU7LVMMXOKM7446XBDC42V","short_pith_number":"pith:KQRAAU7L","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"},"canonical_sha256":"54220053ebab1977299fe73d708c5cd54b37022e9760061182be87743661d9f1","source":{"kind":"arxiv","id":"2310.04406","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.04406","created_at":"2026-05-17T23:38:46Z"},{"alias_kind":"arxiv_version","alias_value":"2310.04406v3","created_at":"2026-05-17T23:38:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.04406","created_at":"2026-05-17T23:38:46Z"},{"alias_kind":"pith_short_12","alias_value":"KQRAAU7LVMMX","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"KQRAAU7LVMMXOKM7","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"KQRAAU7L","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:KQRAAU7LVMMXOKM7446XBDC42V","target":"record","payload":{"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"},"canonical_sha256":"54220053ebab1977299fe73d708c5cd54b37022e9760061182be87743661d9f1","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"},"source_kind":"arxiv","source_id":"2310.04406","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":"2026-05-17T23:38:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v3+XVAk81Xn+WKw/3Dw1kvM5whAq5YuDOq4VteQsEXkqE5R1BlUZ9tM6fDXC660d81ZOSshogYzY7b9stwUrBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T16:51:56.490348Z"},"content_sha256":"ff58ccb880439a8a0d45bc28184d52b26f7a474cf889e814056fec964c8090dd","schema_version":"1.0","event_id":"sha256:ff58ccb880439a8a0d45bc28184d52b26f7a474cf889e814056fec964c8090dd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:KQRAAU7LVMMXOKM7446XBDC42V","target":"graph","payload":{"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"},"verdict_id":"58a4c1bb-024c-4319-b169-45e58f2a7e48"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CT6WbDq+KjERTolZ/c48EP3RBjZD68PoBh7iHYp5iVS4UmBox9NHyt2M/9X3U7kSgrD/DDzJs8Iv1t1S4JZwDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T16:51:56.491342Z"},"content_sha256":"51a4ccde8ce33f3ea029687a936c9fc9d0841be8c5f9d1c8ff295e5856880358","schema_version":"1.0","event_id":"sha256:51a4ccde8ce33f3ea029687a936c9fc9d0841be8c5f9d1c8ff295e5856880358"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KQRAAU7LVMMXOKM7446XBDC42V/bundle.json","state_url":"https://pith.science/pith/KQRAAU7LVMMXOKM7446XBDC42V/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KQRAAU7LVMMXOKM7446XBDC42V/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":"2026-05-22T16:51:56Z","links":{"resolver":"https://pith.science/pith/KQRAAU7LVMMXOKM7446XBDC42V","bundle":"https://pith.science/pith/KQRAAU7LVMMXOKM7446XBDC42V/bundle.json","state":"https://pith.science/pith/KQRAAU7LVMMXOKM7446XBDC42V/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KQRAAU7LVMMXOKM7446XBDC42V/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:KQRAAU7LVMMXOKM7446XBDC42V","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":"f2175a07ca90456aaed3ab5aa5f7ed2f45abc1456dee4d6c1f7af366abc59403","cross_cats_sorted":["cs.CL","cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-10-06T17:55:11Z","title_canon_sha256":"32f9679ff79944b542b9890ca1a452e4bbd2842c0b4f8062941fda58f1d86326"},"schema_version":"1.0","source":{"id":"2310.04406","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.04406","created_at":"2026-05-17T23:38:46Z"},{"alias_kind":"arxiv_version","alias_value":"2310.04406v3","created_at":"2026-05-17T23:38:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.04406","created_at":"2026-05-17T23:38:46Z"},{"alias_kind":"pith_short_12","alias_value":"KQRAAU7LVMMX","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"KQRAAU7LVMMXOKM7","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"KQRAAU7L","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:51a4ccde8ce33f3ea029687a936c9fc9d0841be8c5f9d1c8ff295e5856880358","target":"graph","created_at":"2026-05-17T23:38:46Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Language models use Monte Carlo tree search with self-reflections to plan and act as agents."}],"snapshot_sha256":"5892c298ba859d75ea61aa2dc47d8bb6d764df8491c2e8ee9aa0a1a23f3a91a9"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"9e8bc7682508675408b709a73a7f8b476de14435e933a514458a54ed2e236fc0"},"paper":{"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","authors_text":"Andy Zhou, Haohan Wang, Kai Yan, Michal Shlapentokh-Rothman, Yu-Xiong Wang","cross_cats":["cs.CL","cs.CV","cs.LG"],"headline":"Language models use Monte Carlo tree search with self-reflections to plan and act as agents.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-10-06T17:55:11Z","title":"Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models"},"references":{"count":13,"internal_anchors":7,"resolved_work":13,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Graph of thoughts: Solving elaborate problems with large language models","work_id":"34ed66c5-13ac-4799-b958-8e57d3de4705","year":null},{"cited_arxiv_id":"2107.03374","doi":"","is_internal_anchor":true,"ref_index":2,"title":"Evaluating Large Language Models Trained on Code","work_id":"042493e9-b26f-4b4e-bbde-382072ca9b08","year":null},{"cited_arxiv_id":"2110.14168","doi":"","is_internal_anchor":true,"ref_index":3,"title":"Training Verifiers to Solve Math Word Problems","work_id":"acab1aa8-b4d6-40e0-a3ee-25341701dca2","year":null},{"cited_arxiv_id":"2301.04104","doi":"","is_internal_anchor":true,"ref_index":4,"title":"Mastering Diverse Domains through World Models","work_id":"6aeb260f-8c7c-4f9c-b98b-067cd7c59acd","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"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","year":null}],"snapshot_sha256":"b9d8f897f7b090517e4fe11ad6f64a7325bfeeedb790d403733f144fd63baf18"},"source":{"id":"2310.04406","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-16T23:21:58.759085Z","id":"58a4c1bb-024c-4319-b169-45e58f2a7e48","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"Language models use Monte Carlo tree search with self-reflections to plan and act as agents.","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.","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."}},"verdict_id":"58a4c1bb-024c-4319-b169-45e58f2a7e48"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ff58ccb880439a8a0d45bc28184d52b26f7a474cf889e814056fec964c8090dd","target":"record","created_at":"2026-05-17T23:38:46Z","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":"f2175a07ca90456aaed3ab5aa5f7ed2f45abc1456dee4d6c1f7af366abc59403","cross_cats_sorted":["cs.CL","cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-10-06T17:55:11Z","title_canon_sha256":"32f9679ff79944b542b9890ca1a452e4bbd2842c0b4f8062941fda58f1d86326"},"schema_version":"1.0","source":{"id":"2310.04406","kind":"arxiv","version":3}},"canonical_sha256":"54220053ebab1977299fe73d708c5cd54b37022e9760061182be87743661d9f1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"54220053ebab1977299fe73d708c5cd54b37022e9760061182be87743661d9f1","first_computed_at":"2026-05-17T23:38:46.239259Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:46.239259Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RuNGnTwh0RxMzHSlbkpImf9jPuoc2dTCaNrOeGWCnHLfyVTcFSiYyn/MyFwKA9F9QOsiIr9US74HS0J0f0zbAQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:46.239689Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.04406","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ff58ccb880439a8a0d45bc28184d52b26f7a474cf889e814056fec964c8090dd","sha256:51a4ccde8ce33f3ea029687a936c9fc9d0841be8c5f9d1c8ff295e5856880358"],"state_sha256":"65564b4657d10e77b7dde8517988ee6746324187710c15bbb4763503f55e84dd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NCp8OLqlUgsO1enHIjW3vf1/81XUEy3i6K3+bR7dCb5llr17cryfrJyTeNCubQRbGmS/XyXCLb7GaglNnzL1DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-22T16:51:56.495702Z","bundle_sha256":"301d1ea025f084d9d59db84aeac43854d8771de3b33352a21fca7b255438e2b6"}}