Monte Carlo Tree Search for Execution-Guided Program Repair with Large Language Models

Abstract: Automated program repair with LLMs remains challenging at the repository level due to long-horizon reasoning requirements and the limitations of autoregressive decoding. We present CodePilot, a hybrid framework that integrates Monte Carlo Tree Search (MCTS) with LLMs to enable execution-guided program repair for real-world GitHub issues. CodePilot performs hierarchical fault localization from repository to file and function level, explores diverse patch trajectories using MCTS, and leverages execution feedback as a reward signal to guide search and refinement. The framework further incorporates confidence-calibrated generation to selectively refine low-confidence outputs. Experiments on SWE-bench Lite demonstrate that CodePilot achieves a 24.67% issue resolution rate using open-weight models, outperforming comparable baselines. These results suggest that combining symbolic search with neural LLMs is an effective strategy for scalable, execution-aware software engineering automation.