Teach AI How to Code: Using Large Language Models as Teachable Agents for Programming Education
Open accessAbstract
This work investigates large language models (LLMs) as teachable agents for learning by teaching (LBT). LBT with teachable agents helps learners identify knowledge gaps and discover new knowledge. However, teachable agents require expensive programming of subject-specific knowledge. While LLMs as teachable agents can reduce the cost, LLMs’ expansive knowledge as tutees discourages learners from teaching. We propose a prompting pipeline that restrains LLMs’ knowledge and makes them initiate “why” and “how” questions for effective knowledge-building. We combined these techniques into TeachYou, an LBT environment for algorithm learning, and AlgoBo, an LLM-based tutee chatbot that can simulate misconceptions and unawareness prescribed in its knowledge state. Our technical evaluation confirmed that our prompting pipeline can effectively configure AlgoBo’s problem-solving performance. Through a between-subject study with 40 algorithm novices, we also observed that AlgoBo’s questions led to knowledge-dense conversations (effect size=0.71). Lastly, we discuss design implications, cost-efficiency, and personalization of LLM-based teachable agents.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
LLMs with knowledge graphs can simulate complex learning and assessment scenarios.
“When used with LLMs, they can simulate complex learning and assessment scenarios requiring critical thinking and problem-solving skills, such as in driving education [63], programming education [64], and laboratory safety courses [65].”
From Promises and challenges of generative artificial intelligence for human learning (2024) · cites this paper as [64]
Cites
A revision of bloom's taxonomy: an overview
Krathwohl, D. R. (2002) · Theory Into Practice · doi:10.1207/s15430421tip4104_2 · Cited by 8,132 · see citing works
Training language models to follow instructions with human feedback
Ouyang, L., Wu, J., Jiang, X., Almeida, D., Wainwright, C. L., Mishkin, P., Zhang, C., Agarwal, S., Slama, K., Ray, A., et al. (2022) · arXiv · doi:10.48550/arxiv.2203.02155 · Cited by 4,208 · see citing works
Generative Agents: Interactive Simulacra of Human Behavior
Park, J. S., O'Brien, J., Cai, C. J., Morris, M. R., Liang, P., & Bernstein, M. S. (2023) · Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology · doi:10.1145/3586183.3606763 · Cited by 2,187 · cited 3× · see citing works
“However, LLMs now allow the configuration of agents with natural languages [37, 56], opening new doors for learners to adjust teachable agents for their educational needs.”
Chatbots for learning: A review of educational chatbots for the Facebook Messenger
Smutny, P., & Schreiberova, P. (2020) · Computers & Education · doi:10.1016/j.compedu.2020.103862 · Cited by 770 · see citing works
Exploring Students’ Perceptions of ChatGPT: Thematic Analysis and Follow-Up Survey
Shoufan, A. (2023) · IEEE Access · doi:10.1109/access.2023.3268224 · Cited by 499 · cited 1× · see citing works
“Due to the given persona and unfamiliarity in LBT with virtual agents, many participants put the expectation of a human learner to AlgoBo [66].”
BackgroundPreparing students for future learning with Teachable Agents
Chin, D. B., Dohmen, I. M., Cheng, B. H., Oppezzo, M. A., Chase, C. C., & Schwartz, D. L. (2010) · Educational Technology Research and Development · doi:10.1007/s11423-010-9154-5 · Cited by 119 · see citing works
Conversational agents for fostering curiosity-driven learning in children
Abdelghani, R., Oudeyer, P.-Y., Law, E., de Vulpillières, C., & Sauzéon, H. (2022) · International Journal of Human-Computer Studies · doi:10.1016/j.ijhcs.2022.102887 · Cited by 39 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Promises and challenges of generative artificial intelligence for human learning
Yan, L., Greiff, S., Teuber, Z., & Gašević, D. (2024) · Nature Human Behaviour · doi:10.1038/s41562-024-02004-5 · Cited by 499 · see citing works
“When used with LLMs, they can simulate complex learning and assessment scenarios requiring critical thinking and problemsolving skills, such as in driving education 63 , programming education 64 and laboratory safety courses 65 .”
Alario-Hoyos, C., Kemcha, R., Kloos, C. D., Callejo, P., Estévez-Ayres, I., Santín-Cristóbal, D., Cruz-Argudo, F., & López-Sánchez, J. L. (2024) · 2024 IEEE International Conference on Teaching, Assessment and Learning for Engineering (TALE) · doi:10.1109/tale62452.2024.10834365 · Cited by 8 · see citing works
Navigating the Ethical and Societal Impacts of Generative AI in Higher Computing Education
Mak, J., Nakatumba-Nabende, J., Clear, T., Clear, A., Abluwi, I., Andrei, O., Angeli, L., MacNeil, S., Oyelere, S. S., Hale Rattigan, M., et al. (2025) · Proceedings of the 2025 Working Group Reports on Innovation and Technology in Computer Science Education · doi:10.1145/3760545.3783975 · Cited by 12 · see citing works
Mapeamento Sistemático sobre o Uso de IAs Generativas no Ensino de Programação
Ferreira de Sousa, J., & Silveira, F. R. D. V. (2026) · Revista Eletrônica de Iniciação Científica em Computação · doi:10.5753/reic.2026.7169
- Authors
- Jin, H., Lee, S., Shin, H., & Kim, J.
- Affiliations
- Korea Advanced Institute of Science and Technology (KR)
- Stanford Engineering, Stanford University, United States
- Venue
- Proceedings of the CHI Conference on Human Factors in Computing Systems
- Publisher
- ACM
- Published
- 2024-05-11
- Pages
- 1-28
- OpenAlex
- W4396832972
- Cited by
- 99
- References
- 7
- Citations by year
- 2026: 42 · 2025: 44 · 2024: 13
- FWCI
- 28.58
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- CHI Conference on Human Factors in Computing Systems (publishedVersion, cc-by-nc-sa)
- arXiv (Cornell University) (submittedVersion, cc-by-nc-sa)
- arXiv (Cornell University)
- Funders
- AlgorithmLABS
- Elice
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Intelligent Tutoring Systems and Adaptive Learning
- Physical Sciences › Computer Science › Computer Science Applications › Teaching and Learning Programming
- Physical Sciences › Computer Science › Information Systems › Artificial Intelligence in Education
- Keywords
- large language models, teachable agents, learning by teaching, programming education, algorithm learning, knowledge gap identification, misconceptions, novice programmers, personalized learning
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
