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
Chain-of-Thought and Tree-of-Thoughts are reasoning frameworks that enable models to systematically analyze multi-layered causal relationships.
The Planning module of an Agent is typically implemented based on reasoning frameworks such as Chain-of-Thought (CoT) or ReAct.
Timeline (last 90 days)
Researchers have developed techniques such as self-consistency, tree of thoughts, and verifier reranking to improve the reliability of chain-of-thought.
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 (6)
Chain-of-Thought and Tree-of-Thoughts are reasoning frameworks that enable models to systematically analyze multi-layered causal relationships.
65%VerifiedThe Planning module of an Agent is typically implemented based on reasoning frameworks such as Chain-of-Thought (CoT) or ReAct.
65%UnverifiedResearchers have developed techniques such as self-consistency, tree of thoughts, and verifier reranking to improve the reliability of chain-of-thought.
50%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%