THOUGHTSCULPT: Reasoning with Intermediate Revision and Search
CoRR(2024)
摘要
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
rate), and Constrained Generation (up to +10
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要