{
  "id": "tree-of-thoughts",
  "code": "PTL-0033",
  "term": "Tree of Thoughts",
  "aliases": [
    "ToT"
  ],
  "category": "reasoning",
  "definition": "Tree of Thoughts (ToT) lets a model explore multiple reasoning branches as a search tree, evaluating partial solutions and backtracking, rather than committing to a single left-to-right chain of thought.",
  "description": "Yao et al. combined model-generated candidate thoughts, model self-evaluation of states, and breadth- or depth-first search, producing large gains on tasks such as the Game of 24 that require planning or lookahead.",
  "example": null,
  "broader": [
    "chain-of-thought"
  ],
  "narrower": [
    "graph-of-thoughts"
  ],
  "related": [
    "self-consistency",
    "test-time-compute-scaling"
  ],
  "introduced": 2023,
  "sources": [
    {
      "title": "Tree of Thoughts: Deliberate Problem Solving with Large Language Models",
      "authors": "Yao et al.",
      "year": 2023,
      "url": "https://arxiv.org/abs/2305.10601"
    }
  ],
  "url": "https://protologue.com/t/tree-of-thoughts/",
  "citation": "Protologue. (2026). Tree of Thoughts. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.0.0, PTL-0033). https://protologue.com/t/tree-of-thoughts/"
}