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

2026-01-05

arXiv.org

AI Summary

Debugging skills are crucial in programming education and software development yet are frequently underemphasized in curricula. To address this gap, this work proposes an AI-powered debugging assistant integrated into the IDE that combines retrieval-augmented generation (RAG), large language models, program slicing, and custom heuristic strategies to enhance the accuracy and pedagogical relevance of debugging suggestions while minimizing model invocations. The tool supports efficient debugging by analyzing code in real time, recommending breakpoints, and providing contextual hints. Its effectiveness was validated through a three-tier evaluation encompassing technical assessment, user studies, and in-class deployment, demonstrating significant improvements in debugging efficiency and strong support for instructional practices.

Technology Category

• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Humans and AI: Planning and Decision Support for Human-Machine Teams
• Reasoning under Uncertainty: Probabilistic Programming

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

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.

Problem

• debugging
• programming education
• AI-powered assistance
• IDE integration
• computer science curriculum

Innovation

• AI-powered debugging
• RAG with LLMs
• program slicing
• real-time IDE assistance
• debugging education