How to Teach Programming in the AI Era? Using LLMs as a Teachable Agent for Debugging
Open accessThe DOI matches its Crossref record; 8 of the 8 references it cites were found in a registry or an index.
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.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
GitHub Copilot AI pair programmer: Asset or Liability?
Moradi Dakhel, A., Majdinasab, V., Nikanjam, A., Khomh, F., Desmarais, M. C., & Jiang, Z. M. (. (2023) · Journal of Systems and Software · doi:10.1016/j.jss.2023.111734 · Cited by 417
GitHub Copilot AI pair programmer: Asset or Liability?
Dakhel, A. M., Majdinasab, V., Nikanjam, A., Khomh, F., Desmarais, M. C., Ming, Z., & Jiang (2022) · arXiv · doi:10.48550/arxiv.2206.15331 · Cited by 417 · cited 1×
“We evaluated the generations on six different problems from prior work [Dakhel et al. , 2023] and our own problems (detailed in Table 4 in Supplements).”
Predictability and Surprise in Large Generative Models
Ganguli, D., Hernandez, D., Lovitt, L., DasSarma, N., Henighan, T., Jones, A., Joseph, N., Kernion, J., Mann, B., Askell, A., et al. (2022) · arXiv · doi:10.48550/arxiv.2202.07785 · Cited by 324
Debugging reinvented: asking and answering why and why not questions about program behavior
Ko, A. J., & Myers, B. A. (2008) · Proceedings of the 30th international conference on Software engineering · doi:10.1145/1368088.1368130 · Cited by 296
Predictability and Surprise in Large Generative Models
Ganguli, D., Hernandez, D., Lovitt, L., Askell, A., Bai, Y., Chen, A., Conerly, T., Dassarma, N., Drain, D., Elhage, N., et al. (2022) · 2022 ACM Conference on Fairness Accountability and Transparency · doi:10.1145/3531146.3533229 · Cited by 207 · cited 1×
“Despite their prevalence, LLMs often produce unpredictable mistakes [Ganguli et al. , 2022], e.g., GPT-4 can still make mistakes 17% of the time in coding tasks for introductory and intermediate programming courses [Savelka et al. , 2023].”
Savelka, J., Agarwal, A., An, M., Bogart, C., & Sakr, M. (2023) · Proceedings of the 2023 ACM Conference on International Computing Education Research V.1 · doi:10.1145/3568813.3600142 · Cited by 141 · cited 1×
“Despite their prevalence, LLMs often produce unpredictable mistakes [Ganguli et al. , 2022], e.g., GPT-4 can still make mistakes 17% of the time in coding tasks for introductory and intermediate programming courses [Savelka et al. , 2023].”
Reading Between the Lines: Modeling User Behavior and Costs in AI-Assisted Programming
Mozannar, H., Bansal, G., Fourney, A., & Horvitz, E. (2022) · arXiv · doi:10.48550/arxiv.2210.14306 · Cited by 114 · cited 1×
“Editing times and verification details are in [Ma et al. , 2024].”
Becker, B. A., Denny, P., Finnie-Ansley, J., Luxton-Reilly, A., Prather, J., & Santos, E. A. (2022) · arXiv · doi:10.48550/arxiv.2212.01020 · Cited by 36
Cited by
Shaping the future of higher education: a technology usage study on generative AI innovations
Pang, W., & Wei, Z. (2025) · Information · doi:10.3390/info16020095 · Cited by 52
“[7] introduces an innovative educational tool that integrates LLMs into programming education to enhance students’ debugging skills.”
To Rely or Not to Rely? Evaluating Interventions for Appropriate Reliance on Large Language Models
Bo, J. Y., Wan, S., & Anderson, A. (2025) · Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3714097 · Cited by 36
“We take inspiration from the domain of LLMs for education, where LLMs are prompted to provide guidance or hints instead of direct answers [42, 55].”
How Much Does AI Impact Development Speed? an Enterprise-Based Randomized Controlled Trial
Paradis, E., Grey, K., Madison, Q., Nam, D., Macvean, A., Meimand, V., Zhang, N., Ferrari-Church, B., & Chandra, S. (2025) · 2025 IEEE/ACM 47th International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP) · doi:10.1109/icse-seip66354.2025.00060 · Cited by 20
Enhancing Software Engineering with AI: Key Insights from ChatGPT
Al-Ahmad, A., Kahtan, H., Tahat, L., & Tahat, T. (2024) · 2024 International Conference on Decision Aid Sciences and Applications (DASA) · doi:10.1109/dasa63652.2024.10836262 · Cited by 4
Metadata
- Authors
- Ma, Q., Shen, H., Koedinger, K., & Wu, S. T.
- Venue
- Lecture Notes in Computer Science
- Publisher
- Springer Nature Switzerland
- Published
- 2024
- Pages
- 265-279
- ISSN
- 0302-9743 (ISSN-L)
- 1611-3349
- OpenAlex
- W4400208054
- Cited by
- 63
- References
- 8
- FWCI
- 28.57
- Type
- conference paper
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: How to Teach Programming in the AI Era? Using LLMs as a Teachable Agent for Debugging. https://app.cochat.ai/papers/10.1007/978-3-031-64302-6_19
- The paper
- Ma, Q., Shen, H., Koedinger, K., & Wu, S. T. (2024). How to Teach Programming in the AI Era? Using LLMs as a Teachable Agent for Debugging. Lecture Notes in Computer Science. https://doi.org/10.1007/978-3-031-64302-6_19
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.