@inproceedings{li-etal-2025-rethinkmcts,
    title = "{R}ethink{MCTS}: Refining Erroneous Thoughts in {M}onte {C}arlo Tree Search for Code Generation",
    author = "Li, Qingyao  and
      Xia, Wei  and
      Dai, Xinyi  and
      Du, Kounianhua  and
      Liu, Weiwen  and
      Wang, Yasheng  and
      Tang, Ruiming  and
      Yu, Yong  and
      Zhang, Weinan",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.410/",
    pages = "8103--8121",
    ISBN = "979-8-89176-332-6",
    abstract = "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 \textit{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."
}