English

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

Artificial Intelligence 2024-06-07 v3 Computation and Language Computer Vision and Pattern Recognition Machine Learning

Abstract

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

Keywords

Cite

@article{arxiv.2310.04406,
  title  = {Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models},
  author = {Andy Zhou and Kai Yan and Michal Shlapentokh-Rothman and Haohan Wang and Yu-Xiong Wang},
  journal= {arXiv preprint arXiv:2310.04406},
  year   = {2024}
}

Comments

Code at https://github.com/lapisrocks/LanguageAgentTreeSearch

R2 v1 2026-06-28T12:42:48.888Z