RethinkMCTS: Refining Erroneous Thoughts in Monte Carlo Tree Search for Code Generation
This addresses code generation challenges for developers by improving search quality, though it appears incremental as it builds on existing tree search methods.
The paper tackled the problem of low-quality search in code generation by proposing RethinkMCTS, a framework that refines reasoning processes using execution feedback, resulting in outperformance over previous baselines.
Tree search methods have demonstrated impressive performance in code generation. Previous methods combine tree search with reflection that summarizes past mistakes to achieve iterative improvement. However, these methods face significant challenges. First, they search directly within the code language space, neglecting the underlying reasoning process critical for effective code generation. Second, reflection-based approaches merely accumulate historical errors in memory without providing correct reasoning pathways, making it difficult for subsequent search iterations to identify optimal solutions, resulting in decreased search quality. In this work, we propose RethinkMCTS, a framework that systematically explores and refines the reasoning process for code generation. Specifically, we employ MCTS to search for thoughts before code generation and integrate MCTS with a refinement mechanism called rethink, which incorporates fine-grained code execution feedback to refine erroneous thoughts during the search. It ensures the search path aligns with better reasoning, improving overall search quality. Through extensive experiments, we demonstrate that RethinkMCTS outperforms previous search-based and feedback-enhanced code generation baselines.