Tree of Thoughts: Deliberate Problem Solving with Large Language Models

Authors: Shunyu Yao, Dian Yu, Jeffrey Zhao, Izhak Shafran, Thomas L. Griffiths, Yuan Cao, Karthik Narasimhan (2023)

arXiv: 2305.10601

TLDR (English)

Tree of Thoughts (ToT) models problem solving as tree search: LLMs generate multiple "thought steps" as tree nodes, score them with an evaluator, and search with BFS/DFS. On tasks requiring complex planning (e.g., Game of 24), ToT massively outperforms CoT and is a precursor to o1-style slow thinking.

TLDR（中文）

Tree of Thoughts（ToT）将问题求解建模为树搜索：LLM 生成多个"思维步骤"作为树节点， 用评估函数打分并进行 BFS/DFS 搜索。在需要复杂规划的任务（如 24 点游戏）上， ToT 比普通 CoT 提升巨大，是 o1 风格慢思考的先驱工作。