HomeResearch LibraryTree of Thoughts: Deliberate Problem Solving with Large…
system architectureChapter 1NeurIPS 2023 · 2023

Tree of Thoughts: Deliberate Problem Solving with Large Language Models

Shunyu Yao (Princeton), Dian Yu (Google DeepMind), Jeffrey Zhao (Google DeepMind)

Abstract

We introduce Tree of Thoughts (ToT), a framework that generalizes over the popular Chain of Thought approach to prompting language models, and enables exploration over coherent units of text (thoughts) that serve as intermediate steps toward problem solving.

Key Contributions

  • →Tree-structured thought exploration
  • →BFS/DFS over reasoning steps
  • →Self-evaluation of intermediate thoughts
Eigenvector Commentary

ToT is theoretically powerful but computationally expensive. In enterprise contexts, the cost of exploring multiple reasoning branches must be weighed against the value of the decision. It is most appropriate for high-stakes, low-frequency decisions — not for routine workflow steps.

Topics

planningdeliberate reasoningsearchtree search