tree-of-thought-generalizes-cot

IN premise — entries/2026/06/21/wiki-Prompt_engineering-chunk-1.md

Created 2026-06-21T09:50:10+00:00

Tree-of-thought prompting generalizes chain-of-thought by exploring multiple reasoning paths in parallel with backtracking, using tree search algorithms (breadth-first, depth-first, beam search)

Summary

Instead of forcing a model down a single line of reasoning, tree-of-thought prompting lets it branch into multiple possible paths at once and backtrack when a path dead-ends, much like how a search algorithm explores a tree. This matters because it means reasoning can be much more robust: a wrong turn doesn't derail the whole process, since alternatives are explored in parallel and the best path is selected from the search.

Dependents

These beliefs depend on this one:

OUT inference-compute-reliably-improves-reasoning — Self-consistency (sampling multiple chain-of-thought paths and selecting by majority vote) and Tree of Thoughts (branching reasoning with backtracking) independently demonstrate that LLM reasoning reliability improves with inference-time compute investment — establishing a general compute-for-quality tradeoff at inference time — unless prompt sensitivity means each individual reasoning path is itself unreliable enough to undermine the ensemble.
IN structured-reasoning-prompting-evolved-from-linear-to-branching — Prompting for reasoning evolved from linear chain-of-thought (single path) to self-consistency (multiple paths, majority vote) to tree-of-thoughts (branching with backtracking), progressively adding search structure.