structured-reasoning-prompting-evolved-from-linear-to-branching

IN derived (depth 1)

Created 2026-06-21T09:52:15+00:00 · Reviewed 2026-06-21T14:41:08+00:00

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.

Summary

Getting AI models to reason better has followed a clear progression: first a single step-by-step path, then running several paths and taking a majority vote, and finally exploring a full tree of possibilities with the ability to backtrack and prune dead ends. Each stage layers on more search structure on top of the same underlying model, meaning the gains come not from a smarter architecture but from a smarter way of orchestrating how the model explores its reasoning space.

Justifications

SL — Each technique adds one level of search sophistication: single path → parallel paths → branching paths with backtracking

Antecedents (all must be IN):

  • IN chain-of-thought-prompting-technique — Chain-of-thought prompting (Wei et al. 2022) elicits reasoning by having models show intermediate steps — it is a prompting technique, not an architectural change
  • IN self-consistency-multiple-cot-majority-vote — Self-consistency improves Chain-of-Thought by sampling multiple reasoning paths and selecting the most common conclusion via majority vote (Wang et al., ICLR 2023, arXiv:2203.11171)
  • IN tree-of-thought-generalizes-cot — 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)

Dependents

These beliefs depend on this one: