Structured Reasoning: Least-to-Most / PoT / Tree of Thoughts

Editorial record

Plain-language summary

Tree of Thoughts generalizes chain-of-thought by having the model generate multiple candidate reasoning steps, score them with a value estimate, and search the resulting tree with breadth- or depth-first exploration and backtracking. Least-to-Most decomposes a hard problem into ordered easier subproblems solved in sequence, and Program-of-Thought offloads arithmetic and logic to generated code executed by an interpreter. The shared move is treating reasoning as a structured, evaluable process rather than a single sampled string, which raised accuracy on tasks requiring planning, search, or exact computation.