Tree of Thoughts: Deliberate Problem Solving with Large Language Models

By Shunyu Yao et al

Published on May 17, 2023

Read the original document by opening this link in a new tab.

Table of Contents

1. Introduction
2. Background
3. Tree of Thoughts: Deliberate Problem Solving with LM
4. Experiments

Summary

Language models are increasingly being deployed for general problem solving across a wide range of tasks. This paper introduces a new framework for language model inference, 'Tree of Thoughts' (ToT), which allows LMs to perform deliberate decision making by considering multiple different reasoning paths. ToT significantly enhances language models' problem-solving abilities on tasks requiring non-trivial planning or search. The experiments demonstrate the effectiveness of ToT in improving problem-solving performance using large language models.