Reasoning with Intermediate Revision and Search (THOUGHTSCULPT)
Free while signed in. Answers cite the passages they came from.
THOUGHTSCULPT is a graph-based reasoning framework that combines Monte Carlo Tree Search with an explicit revision action, letting an LLM iteratively rewrite earlier thoughts instead of only extending them.
Revision as a first-class action: Unlike Tree-of-Thoughts, THOUGHTSCULPT allows each node to either extend or revise previous reasoning, producing an interwoven graph of thoughts rather than a pure tree.
MCTS-driven search: Monte Carlo Tree Search navigates the solution space efficiently; evaluation is done with either domain-specific heuristics or an LLM evaluator, giving flexibility across tasks.
Concrete gains: +30% on story outline "interestingness," +16% word success rate on mini-crosswords, and +10% concept coverage on constrained generation, all vs. competitive ToT-style baselines.
Fit for open-ended work: Because revision is built in, THOUGHTSCULPT is especially strong on tasks like creative ideation, multi-step reasoning, and open-ended generation where first drafts are rarely optimal.
Get next week’s papers.
The same picks and the same summaries, in your inbox. Free, and 176 issues deep.
Subscribe on Substack