Enhancing Debugging Skills With AI-Powered Assistance: A Real-Time Tool for Debugging Support

Proceedings of the IEEE/ACM 48th International Conference on Software Engineering 2026 Open access

Read full text
Authors: Elizaveta Artser, Daniil Karol, Anna Potriasaeva, Aleksei Rostovskii, Katsiaryna Dzialets, Ekaterina Koshchenko, Xiaotian Su, April Yi Wang, Anastasiia Birillo
DOI: 10.1145/3786580.3786976
Cited by: 1
References: 36

Abstract

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.

Fields of Study & Subjects

Teaching and Learning Programming Software Testing and Debugging Techniques Software Engineering Techniques and Practices

Publication details

Journal / source
Proceedings of the IEEE/ACM 48th International Conference on Software Engineering
Publisher
ACM
Pages
503–508
Publication date
12 April 2026
Language
EN