Tree of Thoughts
A large language model prompting technique that constructs a tree-structured reasoning process, allowing the model to explore multiple reasoning paths and select the optimal solution. It is an extension of the Chain-of-Thought approach.
Core Facts
Timeline (last 90 days)
Tree of Thoughts (ToT) achieves a more global search by generating multiple candidate thoughts at each step, evaluating their quality, and keeping the best branches, at the cost of a multiplied number of LLM calls.
Tree of Thoughts can require dozens of calls, making it suitable for open-ended design decisions, but it needs a scoring function to judge which paths are better.
In practice it is recommended to first use meta-prompting to clarify the requirements, then use self-consistency to handle key calculations, and enable Tree of Thoughts only when exploratory decisions are truly needed, in order to avoid unnecessary token consumption and latency.
All Facts (4)
The Planning module of an Agent is typically implemented based on reasoning frameworks such as Chain-of-Thought (CoT) or ReAct.
65%UnverifiedTree of Thoughts (ToT) achieves a more global search by generating multiple candidate thoughts at each step, evaluating their quality, and keeping the best branches, at the cost of a multiplied number of LLM calls.
50%UnverifiedTree of Thoughts can require dozens of calls, making it suitable for open-ended design decisions, but it needs a scoring function to judge which paths are better.
50%UnverifiedIn practice it is recommended to first use meta-prompting to clarify the requirements, then use self-consistency to handle key calculations, and enable Tree of Thoughts only when exploratory decisions are truly needed, in order to avoid unnecessary token consumption and latency.
50%