一句话：提出集成于 IDE 的 AI 实时调试助手，结合 RAG、程序切片与启发式，辅助调试教学。
调试是编程教育与软件开发中的关键技能，但在计算机科学课程中常被忽视。本文提出一个集成在 IDE 中的 AI 调试助手，通过实时分析代码、建议断点并提供上下文提示来支持学习者。工具采用基于 LLM 的 RAG、程序切片和自定义启发式策略，以减少 LLM 调用并提升准确性。作者从技术分析、用户体验研究和课堂教学测试三个层面进行评估，结果表明该工具在教授调试技能方面具有应用潜力，并为 AI 辅助调试工具的设计与教育部署提供了初步证据。
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.
@inproceedings{paperbot11971,
title = {Enhancing Debugging Skills With AI-Powered Assistance: A Real-Time Tool for Debugging Support},
author = {Elizaveta Artser and Daniil Karol and Anna Potriasaeva and Aleksei Rostovskii and Katsiaryna Dzialets and Ekaterina Koshchenko and Xiaotian Su and April Yi Wang and Anastasiia Birillo},
booktitle = {ICSE},
year = {2026},
doi = {10.1145/3786580.3786976}
}