Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

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

About

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

Andy Zhou, Kai Yan, Michal Shlapentokh-Rothman, Haohan Wang, Yu-Xiong Wang• 2023

Related benchmarks

TaskDatasetResultRank
Code GenerationHumanEval (test)
Pass@192.7
506
Multitask Language UnderstandingMMLU
Accuracy81.04
413
Mathematical ReasoningSVAMP
Accuracy88.91
403
Arithmetic ReasoningMultiArith
Accuracy93.68
229
Knowledge Graph Question AnsweringCWQ--
166
Web navigation and task completionWebArena (test)
Average Task Completion22.5
137
Code GeneratingMBPP
Pass@181.1
88
Math ReasoningAQUA
Accuracy71.23
78
RegressionCalifornia Housing--
71
Code GenerationAPPS Intermediate
Pass Rate45.86
32
Showing 10 of 62 rows

Other info

Code

Follow for update