TSAPR: A Tree Search Framework For Automated Program Repair

TL;DR

TSAPR introduces a tree search framework for automated program repair that leverages Monte Carlo Tree Search to guide patch exploration, significantly improving repair success rates across multiple benchmarks.

Contribution

It presents TSAPR, a novel evaluate-and-improve framework integrating MCTS for more effective and efficient automated program repair across diverse defect types.

Findings

Successfully repaired 201 out of 835 bugs in Defects4J

Fixed 27 vulnerabilities in VUL4J

Resolved 164 out of 300 issues in SWE-Bench-Lite

Abstract

With the rapid advancement of Large Language Models (LLMs), traditional Automated Program Repair (APR) techniques have undergone significant transformation. Training-free approaches, such as zero-shot and few-shot prompting, are increasingly favored over fine-tuning-based methods, leveraging the strong code understanding and generation capabilities of LLMs to improve repair effectiveness. However, most existing LLM-based APR systems still follow a trial-and-error paradigm, which faces two fundamental challenges: (1) limited patch quality due to myopic, local exploration; and (2) inefficient search processes caused by redundant or unguided patch generation. To address these limitations, we propose TSAPR, a Tree Search-based APR framework designed for diverse types of software defects. Unlike conventional approaches, TSAPR adopts an evaluate-and-improve paradigm that systematically guides the repair process. Specifically, it integrates Monte Carlo Tree Search (MCTS) into patch exploration, enabling global assessment of candidate patches and prioritizing the most promising ones for iterative refinement and generation. By supporting long-trajectory, multi-path exploration, TSAPR significantly enhances search efficiency while maintaining high flexibility and generality. This design makes it applicable to a wide range of defect types and compatible with various base LLMs. We evaluate TSAPR across five widely used bug and vulnerability benchmarks. Experimental results show that TSAPR successfully repairs 201 out of 835 bugs in Defects4J, outperforming all state-of-the-art baselines. TSAPR also fixes 27 of the 79 vulnerabilities in VUL4J and resolves 164 out of 300 issues in SWE-Bench-Lite, demonstrating its broad effectiveness across different defect categories and real-world development scenarios.