# Teach AI How to Code: Using Large Language Models as Teachable Agents for Programming Education

arXiv: https://arxiv.org/abs/2309.14534 · HTML: https://mlsanity.com/paper/2309.14534/

## Key facts

- Cited by 39 papers in the map (data through 14 Oct 2026).
- Placed in Educational agents and math problem solving, one of 16 directions in LLM agents and tool use.
- Builds on 22 of its 125 references that are in the map.
- First posted on arXiv 25 Sep 2023.

## Placed in

- LLM agents and tool use / [Educational agents and math problem solving](https://mlsanity.com/agents/educational-agents-and-math-problem-solving/)

## Builds on (most cited first, 22 of 22)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [WebGPT: Browser-assisted question-answering with human feedback](https://mlsanity.com/paper/2112.09332/) (2021)
- [Large Language Models Can Be Easily Distracted by Irrelevant Context](https://mlsanity.com/paper/2302.00093/) (2023)
- [Fast Model Editing at Scale](https://mlsanity.com/paper/2110.11309/) (2021)
- [Language Models can Solve Computer Tasks](https://mlsanity.com/paper/2303.17491/) (2023)
- [AI Chains: Transparent and Controllable Human-AI Interaction by Chaining Large Language Model Prompts](https://mlsanity.com/paper/2110.01691/) (2021)
- [Evaluating the Ripple Effects of Knowledge Editing in Language Models](https://mlsanity.com/paper/2307.12976/) (2023)
- [Better Zero-Shot Reasoning with Role-Play Prompting](https://mlsanity.com/paper/2308.07702/) (2023)
- [Large Language Model Guided Tree-of-Thought](https://mlsanity.com/paper/2305.08291/) (2023)
- [Leveraging Large Language Models for Multiple Choice Question Answering](https://mlsanity.com/paper/2210.12353/) (2022)
- [SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks](https://mlsanity.com/paper/2305.17390/) (2023)
- [The Programmer's Assistant: Conversational Interaction with a Large Language Model for Software Development](https://mlsanity.com/paper/2302.07080/) (2023)
- [Is ChatGPT a Good Teacher Coach? Measuring Zero-Shot Performance For Scoring and Providing Actionable Insights on Classroom Instruction](https://mlsanity.com/paper/2306.03090/) (2023)
- [Exploring the Intersection of Large Language Models and Agent-Based Modeling via Prompt Engineering](https://mlsanity.com/paper/2308.07411/) (2023)
- [CS1QA: A Dataset for Assisting Code-based Question Answering in an Introductory Programming Course](https://mlsanity.com/paper/2210.14494/) (2022)
- [Conversational agents for fostering curiosity-driven learning in children](https://mlsanity.com/paper/2204.03546/) (2022)
- [Curiosity Notebook: The Design of a Research Platform for Learning by Teaching](https://mlsanity.com/paper/2108.09809/) (2021)
- [Exploring the Curious Case of Code Prompts](https://mlsanity.com/paper/2304.13250/) (2023)

## Built on by (most cited first, 30 of 39)

- [LLM Agents for Education: Advances and Applications](https://mlsanity.com/paper/2503.11733/) (2025)
- [Generative Students: Using LLM-Simulated Student Profiles to Support Question Item Evaluation](https://mlsanity.com/paper/2405.11591/) (2024)
- [CodeXEmbed: A Generalist Embedding Model Family for Multiligual and Multi-task Code Retrieval](https://mlsanity.com/paper/2411.12644/) (2024)
- [TeachTune: Reviewing Pedagogical Agents Against Diverse Student Profiles with Simulated Students](https://mlsanity.com/paper/2410.04078/) (2024)
- [Training Turn-by-Turn Verifiers for Dialogue Tutoring Agents: The Curious Case of LLMs as Your Coding Tutors](https://mlsanity.com/paper/2502.13311/) (2025)
- [SweRank: Software Issue Localization with Code Ranking](https://mlsanity.com/paper/2505.07849/) (2025)
- [Psychometric Alignment: Capturing Human Knowledge Distributions via Language Models](https://mlsanity.com/paper/2407.15645/) (2024)
- [Simulated Students in Tutoring Dialogues: Substance or Illusion?](https://mlsanity.com/paper/2601.04025/) (2026)
- [Understanding the LLM-ification of CHI: Unpacking the Impact of LLMs at CHI through a Systematic Literature Review](https://mlsanity.com/paper/2501.12557/) (2025)
- [When and What to Ask: AskBench and Rubric-Guided RLVR for LLM Clarification](https://mlsanity.com/paper/2602.11199/) (2026)
- [Classroom Simulacra: Building Contextual Student Generative Agents in Online Education for Learning Behavioral Simulation](https://mlsanity.com/paper/2502.02780/) (2025)
- [Beyond the Hype: A Comprehensive Review of Current Trends in Generative AI Research, Teaching Practices, and Tools](https://mlsanity.com/paper/2412.14732/) (2024)
- [Large Language Models in Computer Science Education: A Systematic Literature Review](https://mlsanity.com/paper/2410.16349/) (2024)
- [Evaluating and Optimizing Educational Content with Large Language Model Judgments](https://mlsanity.com/paper/2403.02795/) (2024)
- [The StudyChat Dataset: Analyzing Student Dialogues With ChatGPT in an Artificial Intelligence Course](https://mlsanity.com/paper/2503.07928/) (2025)
- [How AI Coding Agents Modify Code: A Large-Scale Study of GitHub Pull Requests](https://mlsanity.com/paper/2601.17581/) (2026)
- [Towards Valid Student Simulation with Large Language Models](https://mlsanity.com/paper/2601.05473/) (2026)
- [DiLLS: Interactive Diagnosis of LLM-based Multi-agent Systems via Layered Summary of Agent Behaviors](https://mlsanity.com/paper/2602.05446/) (2026)
- [CodeEdu: A Multi-Agent Collaborative Platform for Personalized Coding Education](https://mlsanity.com/paper/2507.13814/) (2025)
- [Carbon and Silicon, Coexist or Compete? A Survey on Human-AI Interactions in Agent-based Modeling and Simulation](https://mlsanity.com/paper/2502.18145/) (2025)
- [Synthesizing High-Quality Programming Tasks with LLM-based Expert and Student Agents](https://mlsanity.com/paper/2504.07655/) (2025)
- [Evolution in Simulation: AI-Agent School with Dual Memory for High-Fidelity Educational Dynamics](https://mlsanity.com/paper/2510.11290/) (2025)
- [Simulating Novice Students Using Machine Unlearning and Relearning in Large Language Models](https://mlsanity.com/paper/2603.26142/) (2026)
- [Designing Conversational AI to Support Think-Aloud Practice in Technical Interview Preparation for CS Students](https://mlsanity.com/paper/2507.14418/) (2025)
- [Reasoning Planning for Language Models](https://mlsanity.com/paper/2511.00521/) (2025)
- [Interpretable Difficulty-Aware Knowledge Tracing in Tutor-Student Dialogues](https://mlsanity.com/paper/2605.01097/) (2026)
- [Students' Perceived Roles, Opportunities, and Challenges of a Generative AI-powered Teachable Agent: A Case of Middle School Math Class](https://mlsanity.com/paper/2409.06721/) (2024)
- [Human-Human-AI Triadic Programming: Uncovering the Role of AI Agent and the Value of Human Partner in Collaborative Learning](https://mlsanity.com/paper/2601.12134/) (2026)
- [KnowSim: Evaluating Information Calibration in LLM Assistants with User Simulators that Learn](https://mlsanity.com/paper/2608.17150/) (2026)
- [Beyond prior knowledge: The predictive role of knowledge-building in Tutor Learning](https://mlsanity.com/paper/2508.18545/) (2025)

## Abstract (arXiv)

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.