A Unified Debugging Approach via LLM-Based Multi-Agent Synergy
arxiv(2024)
摘要
Tremendous efforts have been devoted to automating software debugging, a
time-consuming process involving fault localization and repair generation.
Recently, Large Language Models (LLMs) have shown great potential in automated
debugging. However, we identified three challenges posed to traditional and
LLM-based debugging tools: 1) the upstream imperfection of fault localization
affects the downstream repair, 2) the deficiency in handling complex logic
errors, and 3) the ignorance of program contexts. In this context, we propose
the first automated, unified debugging framework, FixAgent, via LLM agent
synergy. FixAgent can perform end-to-end localization, repair, and analysis of
bugs. Our insight is that LLMs can benefit from general software engineering
principles recognized by human developers in debugging, such as rubber duck
debugging, enabling a better understanding of program functionality and logic
bugs. Hence, we create three designs inspired by rubber ducking to address
these challenges. They are agent specialization and synergy, key variable
tracking, and program context comprehension, which request LLMs to provide
explicit explanations and force them to focus on crucial program logic
information. Experiments on the widely used dataset QuixBugs show that FixAgent
correctly fixes 79 out of 80 bugs, 9 of which have never been fixed. It also
plausibly patches 1.9X more defects than the best-performing repair tool on
CodeFlaws, even with no bug location information and fewer than 0.6
times. On average, FixAgent increases about 20
compared to its base model using different LLMs, showing the effectiveness of
our designs. Moreover, the correctness rate of FixAgent reaches remarkably
97.26
of the existing approaches.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要