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

• URL: http://arxiv.org/abs/2602.00129v1
• Date: Wed, 28 Jan 2026 03:12:14 GMT
• Title: Monte Carlo Tree Search for Execution-Guided Program Repair with Large Language Models
• Authors: Yixuan Liang,
• Abstract summary: We present CodePilot, a hybrid framework that integrates Monte Carlo Tree Search (MCTS) with large language models to enable execution-guided program repair for real-world GitHub issues.<n>Experiments on SWE-bench Lite demonstrate that CodePilot achieves a 24.67% issue resolution rate using open-weight models, outperforming comparable baselines.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Automated program repair with large language models 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 large language models 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 language models is an effective strategy for scalable, execution-aware software engineering automation.

Related papers

• Code Fingerprints: Disentangled Attribution of LLM-Generated Code [7.515488307576106]
  We study the problem of model-level code attribution, which aims to determine the source LLM responsible for generated code.<n>We propose the Disentangled Code Attribution Network (DCAN), which separates Source-Agnostic semantic information from Source-Specific stylistic representations.<n>We construct the first large-scale benchmark dataset comprising code generated by four widely used Large Language Models (LLMs) across four programming languages.
  arXiv  Detail & Related papers  (2026-03-04T15:58:36Z)
• Thinking with Programming Vision: Towards a Unified View for Thinking with Images [23.596757163808906]
  We show that even state-of-the-art MLLMs are surprisingly brittle, showing significant performance degradation on images with simple orientation changes or natural corruptions.<n>We propose CodeVision, a flexible and scalable code-as-tool framework where the model generates code as a universal interface to invoke any image operation.
  arXiv  Detail & Related papers  (2025-12-03T12:44:15Z)
• Asm2SrcEval: Evaluating Large Language Models for Assembly-to-Source Code Translation [4.45354703148321]
  Assembly-to-source code translation is a critical task in reverse engineering, cybersecurity, and software maintenance.<n>We present the first comprehensive evaluation of five state-of-the-art large language models on assembly-to-source translation.
  arXiv  Detail & Related papers  (2025-11-28T12:40:30Z)
• SWE-Compass: Towards Unified Evaluation of Agentic Coding Abilities for Large Language Models [59.90381306452982]
  evaluating large language models (LLMs) for software engineering has been limited by narrow task coverage, language bias, and insufficient alignment with real-world developer.<n>We introduce SWE-1, a comprehensive benchmark that unifies heterogeneous code-related evaluations into a structured and production-aligned framework.<n>SWE- spans 8 task types, 8 programming scenarios, and 10 programming languages, with 2000 high-quality instances curated from authentic GitHub pull requests.
  arXiv  Detail & Related papers  (2025-11-07T18:01:32Z)
• SwingArena: Competitive Programming Arena for Long-context GitHub Issue Solving [90.32201622392137]
  We present SwingArena, a competitive evaluation framework for Large Language Models (LLMs)<n>Unlike traditional static benchmarks, SwingArena models the collaborative process of software by pairing LLMs as iterations, who generate patches, and reviewers, who create test cases and verify the patches through continuous integration (CI) pipelines.
  arXiv  Detail & Related papers  (2025-05-29T18:28:02Z)
• SweRank: Software Issue Localization with Code Ranking [109.3289316191729]
  SweRank is an efficient retrieve-and-rerank framework for software issue localization.<n>We construct SweLoc, a large-scale dataset curated from public GitHub repositories.<n>We show that SweRank achieves state-of-the-art performance, outperforming both prior ranking models and costly agent-based systems.
  arXiv  Detail & Related papers  (2025-05-07T19:44:09Z)
• ToolCoder: A Systematic Code-Empowered Tool Learning Framework for Large Language Models [81.12673534903979]
  Tool learning has emerged as a crucial capability for large language models (LLMs) to solve complex real-world tasks through interaction with external tools.<n>We propose ToolCoder, a novel framework that reformulates tool learning as a code generation task.
  arXiv  Detail & Related papers  (2025-02-17T03:42:28Z)
• CodeTree: Agent-guided Tree Search for Code Generation with Large Language Models [106.11371409170818]
  Large language models (LLMs) can act as agents with capabilities to self-refine and improve generated code autonomously. We propose CodeTree, a framework for LLM agents to efficiently explore the search space in different stages of the code generation process. Specifically, we adopted a unified tree structure to explicitly explore different coding strategies, generate corresponding coding solutions, and subsequently refine the solutions.
  arXiv  Detail & Related papers  (2024-11-07T00:09:54Z)
• Generating Code World Models with Large Language Models Guided by Monte Carlo Tree Search [5.913758275518443]
  We consider Code World Models, world models generated by a Large Language Model (LLM) in the form of Python code for model-based Reinforcement Learning (RL) Calling code instead of LLMs for planning has potential to be more precise, reliable, interpretable, and extremely efficient. We show that the Code World Models synthesized with it can be successfully used for planning, resulting in model-based RL agents with greatly improved sample efficiency and inference speed.
  arXiv  Detail & Related papers  (2024-05-24T09:31:26Z)
• Sequential Monte Carlo Steering of Large Language Models using Probabilistic Programs [46.721838623748816]
  We propose a new inference-time approach to enforcing syntactic and semantic constraints on the outputs of large language models. Key idea is to specify language generation tasks as posterior inference problems in a class of discrete probabilistic sequence models. For a computational cost similar to that of beam search, SMC can steer LLMs to solve diverse tasks.
  arXiv  Detail & Related papers  (2023-06-05T17:55:05Z)
• CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning [92.36705236706678]
  "CodeRL" is a new framework for program synthesis tasks through pretrained LMs and deep reinforcement learning. During inference, we introduce a new generation procedure with a critical sampling strategy. For the model backbones, we extended the encoder-decoder architecture of CodeT5 with enhanced learning objectives.
  arXiv  Detail & Related papers  (2022-07-05T02:42:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.