AAMAS Conference 2026 Conference Paper
DebugTA: An LLM-Based Agent for Simplifying Debugging and Teaching in Programming Education
- Lingyue Fu
- Datong Chen
- Haowei Yuan
- Xinyi Dai
- Qingyao Li
- Weinan Zhang
- Weiwen Liu
- Yong Yu
In programming education, Debugging and Teaching (DT) task is a common scenario which requires generating modification suggestions from erroneous code, error messages, reference solutions, and problem descriptions. Existing approaches struggle with complex multi-source reasoning and underutilize available reference code, limiting the effectiveness of large language models (LLMs) in DT tasks. To address these challenges, we propose DebugTA, a novel LLM-based debugging and teaching agent with specialized tools for standard code retrieval, variable substitution to align reference code, and an external compiler for real-time code analysis. Guided by pedagogical and debugging principles, DebugTA decomposes complexDTtasksintostructuredLLM–toolinteractionsthatreduce reasoning complexity. By aligning reference code with erroneous code, DebugTA enables the LLM to focus on logical errors and improves suggestion accuracy. To rigorously assess the quality of modification suggestions, we introduce a student simulator-teacher interactionparadigm. Experimentalresultsonthreereal-worldcode datasets demonstrate that DebugTA consistently improves teaching effectiveness while significantly reducing computational costs.