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

By Andy Zhou, Kai Yan, Michal Shlapentokh-Rothman, Haohan Wang, Yu-Xiong Wang. International Conference on Machine Learning, 2023

568 citations recorded by the source corpus.

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

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/700bd9681f1b9e9e2212e10415d27b11c7e6836b

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection (2023, background): “Yet, the improved task performance of such approaches often comes at the expense of run-time efficiency (Mallen et al., 2023), robustness to irrelevant context (Shi et al., 2023), and lack of attributions (Liu et al., 2023a; Gao et al., 2023).”
A Survey on Large Language Models for Code Generation (2024, unknown): “The results show that the pass-ratio@n can provide more granular insight than the pass@k metrics.”
s1: Simple test-time scaling (2025, unknown): “This approach significantly boosts GPQA performance but overall still falls short of using s1K .”
AppAgent: Multimodal Agents as Smartphone Users (2023, unknown): “Language Agent Tree Search [52] combines Monte Carlo Tree Search with LLMs to improve multi-step reasoning and planning for autonomous agents, achieving state-of-the-art results in tasks like programming and web navigation.”
CodeScope: An Execution-based Multilingual Multitask Multidimensional Benchmark for Evaluating LLMs on Code Understanding and Generation (2023, methodology): “In the Appendix, we provide a detailed case study in Tables 45 to better understand our program synthesis task.”
CodeARC: Benchmarking Reasoning Capabilities of LLM Agents for Inductive Program Synthesis (2025, unknown): “LLM-powered Agents LLM-based agents have shown strong performance in domains like web navigation (Zhou et al., 2024a;b), code generation (Zhang et al., 2023; Jimenez et al., 2024), performance optimization (Wei et al., 2025b;c), and ML experimentation (Huang et al., 2024).”