Debugging is a crucial skill in programming education and software development, yet it is often overlooked in CS curricula. To address this, we introduce an AI-powered debugging assistant integrated into an IDE. It offers real-time support by analyzing code, suggesting breakpoints, and providing contextual hints. Using RAG with LLMs, program slicing, and custom heuristics, it enhances efficiency by minimizing LLM calls and improving accuracy. A three-level evaluation - technical analysis, UX study, and classroom tests - highlights its potential for teaching debugging.

翻译：调试是编程教育和软件开发中的关键技能，但在计算机科学课程中常被忽视。为此，我们提出了一种集成于IDE的人工智能调试助手。该工具通过分析代码、建议断点并提供上下文提示，提供实时支持。它结合了基于检索增强生成（RAG）的大语言模型、程序切片和自定义启发式方法，通过减少大语言模型调用次数并提高准确性来提升调试效率。通过技术分析、用户体验研究和课堂测试三个层面的评估，该工具展现了其在调试教学中的潜力。