@inproceedings{chi-etal-2025-thoughtsculpt,
    title = "{T}hought{S}culpt: Reasoning with Intermediate Revision and Search",
    author = "Chi, Yizhou  and
      Yang, Kevin  and
      Klein, Dan",
    editor = "Chiruzzo, Luis  and
      Ritter, Alan  and
      Wang, Lu",
    booktitle = "Findings of the Association for Computational Linguistics: NAACL 2025",
    month = apr,
    year = "2025",
    address = "Albuquerque, New Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2025.findings-naacl.428/",
    pages = "7685--7711",
    ISBN = "979-8-89176-195-7",
    abstract = "We present THOUGHTSCULPT, a general reasoning and search method for tasks with outputs that can be decomposed into components. THOUGHTSCULPT explores a search tree of potential solutions using Monte Carlo Tree Search (MCTS), building solutions one action at a time and evaluating according to any domain-specific heuristic, which in practice is often simply an LLM evaluator. Critically, our action space includes revision actions: THOUGHTSCULPT may choose to revise part of its previous output rather than continuing to build the rest of its output. Empirically, THOUGHTSCULPT outperforms state-of-the-art reasoning methods across three challenging tasks: Story Outline Improvement (up to +30{\%} interestingness), Mini-Crosswords Solving (up to +16{\%} word success rate), and Constrained Generation (up to +10{\%} concept coverage)."
}