MarsCode Agent: AI-native Automated Bug Fixing

TL;DR

MarsCode Agent is an innovative framework that uses large language models combined with code analysis to automatically identify, localize, and repair bugs in real-world software systems, demonstrating high success rates.

Contribution

It introduces a systematic approach integrating LLMs with code analysis for automated bug fixing, improving accuracy and effectiveness over existing methods.

Findings

High success rate in bug fixing on SWE-bench

Effective fault localization and patch generation

Outperforms most existing automated approaches

Abstract

Recent advances in large language models (LLMs) have shown significant potential to automate various software development tasks, including code completion, test generation, and bug fixing. However, the application of LLMs for automated bug fixing remains challenging due to the complexity and diversity of real-world software systems. In this paper, we introduce MarsCode Agent, a novel framework that leverages LLMs to automatically identify and repair bugs in software code. MarsCode Agent combines the power of LLMs with advanced code analysis techniques to accurately localize faults and generate patches. Our approach follows a systematic process of planning, bug reproduction, fault localization, candidate patch generation, and validation to ensure high-quality bug fixes. We evaluated MarsCode Agent on SWE-bench, a comprehensive benchmark of real-world software projects, and our results show that MarsCode Agent achieves a high success rate in bug fixing compared to most of the existing automated approaches.