Papers › Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models

Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models

6 Oct 2023arXiv:2310.04406archive 2025-07-28

Andy Zhou, Kai Yan, Michal Shlapentokh-Rothman, Haohan Wang, Yu-Xiong Wang

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 feature of our approach is the incorporation of an environment for external feedback, which offers a more deliberate and adaptive problem-solving mechanism that surpasses the constraints of existing techniques. Our experimental evaluation across diverse domains, including programming, interactive question-answering (QA), web navigation, and math, validates the effectiveness and generality of LATS in decision-making while maintaining competitive or improved reasoning performance. Notably, 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. Code can be found at https://github.com/lapisrocks/LanguageAgentTreeSearch

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2310.04406")

Code

Syntology Ran 7 of 9 code samples harvested from 1 repository linked to this paper; 2 have no recorded run. Of those that ran: 1 ran · honoured contract; 1 ran · our draft was wrong; 5 ran with no contract checked.

By repository: official repository: 9 samples from 1 repository, 7 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

lapisrocks/languageagenttreesearch officialmentioned in papermentioned on GitHubMIT report
andyz245/LanguageAgentTreeSearch officialmentioned on GitHubMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

9 samples harvested; 7 ran; 1 honoured the contract we drafted; 2 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · honoured contract
1ran · our draft was wrong
5ran
2unverified

Licence: 0 of the 9 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from andyz245/LanguageAgentTreeSearch. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

clean_str andyz245/LanguageAgentTreeSearch/hotpot/wikienv.py official repository ran fingerprinted MIT (permissive) · 950bad9206459619 · report
f1_score andyz245/LanguageAgentTreeSearch/hotpot/wrappers.py official repository ran · honoured contract MIT (permissive) · 32a5f1733d9a8971 · report
gather_context_from_tree andyz245/LanguageAgentTreeSearch/programming/dfs.py official repository ran MIT (permissive) · 9a161c157833c2ee · report
gpt3 andyz245/LanguageAgentTreeSearch/webshop/models.py official repository ran MIT (permissive) · 4917a312cc817135 · report
gpt_completion andyz245/LanguageAgentTreeSearch/programming/generators/model.py official repository ran MIT (permissive) · c39e62f1641b4200 · report
normalize_answer andyz245/LanguageAgentTreeSearch/hotpot/wrappers.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · dae7ab386661a4f4 · report
prune_context_blocks andyz245/LanguageAgentTreeSearch/programming/dfs.py official repository ran fingerprinted MIT (permissive) · 5a1d885f39975a81 · report
message_to_str andyz245/LanguageAgentTreeSearch/programming/generators/model.py official repository unverified MIT (permissive) · a067a230397d97aa · report
messages_to_str andyz245/LanguageAgentTreeSearch/programming/generators/model.py official repository unverified MIT (permissive) · 4e0f76b9ec8bd13a · report

Tasks

Code GenerationDecision MakingHumanEvalIn-Context LearningMathModel-based Reinforcement LearningQuestion Answering

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Code Generation MBPP o1-mini + Language Agent Tree Search (Hamming.ai) Accuracy 82.3 #18 of 99 Archive leaderboard report
Code Generation MBPP GPT-3.5 Turbo + Language Agent Tree Search Accuracy 81.1 #20 of 99 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Absolute Position EncodingsAdamAttentionAttention DropoutBPECosine AnnealingDense ConnectionsDropoutGPT-3GPT-4Label SmoothingLayer NormalizationLinear LayerLinear Warmup With Cosine AnnealingMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformerWeight Decay

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections