How to Teach Programming in the AI Era? Using LLMs as a Teachable Agent for Debugging (Extended Abstract)

Ma, Qianou; Shen, Hua; Koedinger, Ken; Wu, Tongshuang

doi:10.24963/ijcai.2025/1217

How to Teach Programming in the AI Era? Using LLMs as a Teachable Agent for Debugging (Extended Abstract)

Qianou Ma, Hua Shen, Ken Koedinger, Tongshuang Wu

Download BibTeX Cite

Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence. Sister Conferences Best Papers. Pages 10922-10926.

https://doi.org/10.24963/ijcai.2025/1217

Keywords

Sister Conferences Best Papers: Humans and AI
Sister Conferences Best Papers: Multidisciplinary Topics and Applications
Sister Conferences Best Papers: Agent-based and Multi-agent Systems

Abstract

Large Language Models (LLMs) excel at generating content at impeccable speeds. However, they are imperfect and still make various mistakes. In Computer Science education, as LLMs are widely recognized as "AI pair programmers," it becomes increasingly important to train students on evaluating and debugging LLM-generated codes. In this work, we introduce HypoCompass, a novel system to facilitate deliberate practice on debugging, where human novices play the role of Teaching Assistants and help LLM-powered teachable agents debug code.

We enable effective task delegation between students and LLMs in this learning-by-teaching environment: students focus on hypothesizing the cause of code errors, while adjacent skills like code completion are offloaded to LLM-agents. Our evaluations demonstrate that HypoCompass generates high-quality training materials (e.g., bugs and fixes), outperforming human counterparts fourfold in efficiency, and significantly improves student performance on debugging by 12% in the pre-to-post test.

Qianou Ma, Hua Shen, Ken Koedinger, and Tongshuang Wu. 2025. How to Teach Programming in the AI Era? Using LLMs as a Teachable Agent for Debugging (Extended Abstract). In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25. IJCAI, 10922–10926. https://doi.org/10.24963/ijcai.2025/1217

@inproceedings{ijcai2025p1217,
  title     = {How to Teach Programming in the AI Era? Using LLMs as a Teachable Agent for Debugging (Extended Abstract)},
  author    = {Ma, Qianou and Shen, Hua and Koedinger, Ken and Wu, Tongshuang},
  booktitle = {Proceedings of the Thirty-Fourth International Joint Conference on
               Artificial Intelligence, {IJCAI-25}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {James Kwok},
  pages     = {10922--10926},
  year      = {2025},
  month     = {8},
  note      = {Sister Conferences Best Papers},
  doi       = {10.24963/ijcai.2025/1217},
  url       = {https://doi.org/10.24963/ijcai.2025/1217},
}

TY  - CPAPER
TI  - How to Teach Programming in the AI Era? Using LLMs as a Teachable Agent for Debugging (Extended Abstract)
AU  - Ma, Qianou
AU  - Shen, Hua
AU  - Koedinger, Ken
AU  - Wu, Tongshuang
T2  - Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2025
SP  - 10922
EP  - 10926
DO  - 10.24963/ijcai.2025/1217
UR  - https://doi.org/10.24963/ijcai.2025/1217
ER  -