Teach AI How to Code: Using Large Language Models as Teachable Agents for Programming Education
On the map: LLM agents and tool use → Educational agents and math problem solving
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.
Key facts. Cited by 38 papers in the map (data through 7 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.
Builds on
22 of 125 references.
References · 22
- 2020Language Models are Few-Shot Learnerscited by 32,199
- 2022Training language models to follow instructions with human feedbackcited by 15,712
- 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
- 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
- 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,155
- 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,722
- 2023Large Language Models Can Be Easily Distracted by Irrelevant Contextcited by 820
- 2021Fast Model Editing at Scalecited by 491
- 2023Language Models can Solve Computer Taskscited by 371
- 2021AI Chains: Transparent and Controllable Human-AI Interaction by Chaining Large Language Model Promptscited by 265
- 2023Evaluating the Ripple Effects of Knowledge Editing in Language Modelscited by 238
- 2023Better Zero-Shot Reasoning with Role-Play Promptingcited by 220
10 more
- 2023Large Language Model Guided Tree-of-Thoughtcited by 218
- 2022Leveraging Large Language Models for Multiple Choice Question Answeringcited by 199
- 2023SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Taskscited by 166
- 2023The Programmer's Assistant: Conversational Interaction with a Large Language Model for Software Developmentcited by 95
- 2023Is ChatGPT a Good Teacher Coach? Measuring Zero-Shot Performance For Scoring and Providing Actionable Insights on Classroom Instructioncited by 37
- 2023Exploring the Intersection of Large Language Models and Agent-Based Modeling via Prompt Engineeringcited by 17
- 2022CS1QA: A Dataset for Assisting Code-based Question Answering in an Introductory Programming Coursecited by 11
- 2022Conversational agents for fostering curiosity-driven learning in childrencited by 7
- 2021Curiosity Notebook: The Design of a Research Platform for Learning by Teachingcited by 6
- 2023Exploring the Curious Case of Code Promptscited by 6
Built on by
Citing papers per year: 2024: 8; 2025: 18; 2026: 12.
38 papers.
Sort:
By area:
- 2025LLM Agents for Education: Advances and Applicationscited by 59
- 2024Generative Students: Using LLM-Simulated Student Profiles to Support Question Item Evaluationcited by 56
- 2024CodeXEmbed: A Generalist Embedding Model Family for Multiligual and Multi-task Code Retrievalcited by 33
- 2024TeachTune: Reviewing Pedagogical Agents Against Diverse Student Profiles with Simulated Studentscited by 25
- 2025SweRank: Software Issue Localization with Code Rankingcited by 20
- 2024Psychometric Alignment: Capturing Human Knowledge Distributions via Language Modelscited by 18
- 2025Training Turn-by-Turn Verifiers for Dialogue Tutoring Agents: The Curious Case of LLMs as Your Coding Tutorscited by 17
- 2025Understanding the LLM-ification of CHI: Unpacking the Impact of LLMs at CHI through a Systematic Literature Reviewcited by 16
- 2025Classroom Simulacra: Building Contextual Student Generative Agents in Online Education for Learning Behavioral Simulationcited by 15
- 2026Simulated Students in Tutoring Dialogues: Substance or Illusion?cited by 14
- 2024Beyond the Hype: A Comprehensive Review of Current Trends in Generative AI Research, Teaching Practices, and Toolscited by 13
- 2024Large Language Models in Computer Science Education: A Systematic Literature Reviewcited by 12
26 more
- 2026When and What to Ask: AskBench and Rubric-Guided RLVR for LLM Clarificationcited by 12
- 2024Evaluating and Optimizing Educational Content with Large Language Model Judgmentscited by 11
- 2025The StudyChat Dataset: Analyzing Student Dialogues With ChatGPT in an Artificial Intelligence Coursecited by 7
- 2026Towards Valid Student Simulation with Large Language Modelscited by 7
- 2026How AI Coding Agents Modify Code: A Large-Scale Study of GitHub Pull Requestscited by 7
- 2026DiLLS: Interactive Diagnosis of LLM-based Multi-agent Systems via Layered Summary of Agent Behaviorscited by 7
- 2025CodeEdu: A Multi-Agent Collaborative Platform for Personalized Coding Educationcited by 4
- 2025Carbon and Silicon, Coexist or Compete? A Survey on Human-AI Interactions in Agent-based Modeling and Simulationcited by 3
- 2025Synthesizing High-Quality Programming Tasks with LLM-based Expert and Student Agentscited by 3
- 2025Evolution in Simulation: AI-Agent School with Dual Memory for High-Fidelity Educational Dynamicscited by 3
- 2025Designing Conversational AI to Support Think-Aloud Practice in Technical Interview Preparation for CS Studentscited by 2
- 2025Reasoning Planning for Language Modelscited by 2
- 2024Students' Perceived Roles, Opportunities, and Challenges of a Generative AI-powered Teachable Agent: A Case of Middle School Math Classcited by 1
- 2026Human-Human-AI Triadic Programming: Uncovering the Role of AI Agent and the Value of Human Partner in Collaborative Learningcited by 1
- 2025Beyond prior knowledge: The predictive role of knowledge-building in Tutor Learningcited by 0
- 2025Feed-O-Meter: Investigating AI-Generated Mentee Personas as Interactive Agents for Scaffolding Design Feedback Practicecited by 0
- 2025Chrysalis: A Unified System for Comparing Active Teaching and Passive Learning with AI Agents in Educationcited by 0
- 2025Student Development Agent: Risk-free Simulation for Evaluating AIED Innovationscited by 0
- 2025DebugTA: An LLM-Based Agent for Simplifying Debugging and Teaching in Programming Educationcited by 0
- 2025Argus: A Multi-Agent Sensitive Information Leakage Detection Framework Based on Hierarchical Reference Relationshipscited by 0
- 2026The RIGID Framework: Research-Integrated, Generative AI-Mediated Instructional Designcited by 0
- 2026Interpretable Difficulty-Aware Knowledge Tracing in Tutor-Student Dialoguescited by 0
- 2026CPEMH: An Agentic Framework for Prompt-Driven Behavior Evaluation and Assurance in Foundation-Model Systems for Mental Health Screeningcited by 0
- 2026In-IDE Toolkit for Developers of AI-Based Featurescited by 0
- 2026KnowSim: Evaluating Information Calibration in LLM Assistants with User Simulators that Learncited by 0
- 2026Oops, Not Now: PEARL, a RAG-Based Support Agent for Gameplay and What Players Want from AI Helpcited by 0
- 2026Oops, Not Now: PEARL, a RAG-Based Support Agent for Gameplay and What Players Want from AI Help12 Sep 2026
- 2026KnowSim: Evaluating Information Calibration in LLM Assistants with User Simulators that Learn17 Aug 2026
- 2026In-IDE Toolkit for Developers of AI-Based Features14 May 2026
- 2026CPEMH: An Agentic Framework for Prompt-Driven Behavior Evaluation and Assurance in Foundation-Model Systems for Mental Health Screening11 May 2026
- 2026Interpretable Difficulty-Aware Knowledge Tracing in Tutor-Student Dialogues1 May 2026
- 2026The RIGID Framework: Research-Integrated, Generative AI-Mediated Instructional Design13 Mar 2026
- 2026DiLLS: Interactive Diagnosis of LLM-based Multi-agent Systems via Layered Summary of Agent Behaviors5 Feb 2026
- 2026When and What to Ask: AskBench and Rubric-Guided RLVR for LLM Clarification4 Feb 2026
- 2026How AI Coding Agents Modify Code: A Large-Scale Study of GitHub Pull Requests24 Jan 2026
- 2026Human-Human-AI Triadic Programming: Uncovering the Role of AI Agent and the Value of Human Partner in Collaborative Learning17 Jan 2026
- 2026Towards Valid Student Simulation with Large Language Models9 Jan 2026
- 2026Simulated Students in Tutoring Dialogues: Substance or Illusion?7 Jan 2026
26 more
- 2025Argus: A Multi-Agent Sensitive Information Leakage Detection Framework Based on Hierarchical Reference Relationships9 Dec 2025
- 2025Reasoning Planning for Language Models1 Nov 2025
- 2025Evolution in Simulation: AI-Agent School with Dual Memory for High-Fidelity Educational Dynamics13 Oct 2025
- 2025DebugTA: An LLM-Based Agent for Simplifying Debugging and Teaching in Programming Education13 Oct 2025
- 2025Student Development Agent: Risk-free Simulation for Evaluating AIED Innovations10 Oct 2025
- 2025Chrysalis: A Unified System for Comparing Active Teaching and Passive Learning with AI Agents in Education6 Oct 2025
- 2025Feed-O-Meter: Investigating AI-Generated Mentee Personas as Interactive Agents for Scaffolding Design Feedback Practice9 Sep 2025
- 2025Beyond prior knowledge: The predictive role of knowledge-building in Tutor Learning25 Aug 2025
- 2025Designing Conversational AI to Support Think-Aloud Practice in Technical Interview Preparation for CS Students19 Jul 2025
- 2025CodeEdu: A Multi-Agent Collaborative Platform for Personalized Coding Education18 Jul 2025
- 2025SweRank: Software Issue Localization with Code Ranking7 May 2025
- 2025Synthesizing High-Quality Programming Tasks with LLM-based Expert and Student Agents10 Apr 2025
- 2025LLM Agents for Education: Advances and Applications14 Mar 2025
- 2025The StudyChat Dataset: Analyzing Student Dialogues With ChatGPT in an Artificial Intelligence Course11 Mar 2025
- 2025Carbon and Silicon, Coexist or Compete? A Survey on Human-AI Interactions in Agent-based Modeling and Simulation25 Feb 2025
- 2025Training Turn-by-Turn Verifiers for Dialogue Tutoring Agents: The Curious Case of LLMs as Your Coding Tutors18 Feb 2025
- 2025Classroom Simulacra: Building Contextual Student Generative Agents in Online Education for Learning Behavioral Simulation4 Feb 2025
- 2025Understanding the LLM-ification of CHI: Unpacking the Impact of LLMs at CHI through a Systematic Literature Review22 Jan 2025
- 2024Beyond the Hype: A Comprehensive Review of Current Trends in Generative AI Research, Teaching Practices, and Tools19 Dec 2024
- 2024CodeXEmbed: A Generalist Embedding Model Family for Multiligual and Multi-task Code Retrieval19 Nov 2024
- 2024Large Language Models in Computer Science Education: A Systematic Literature Review21 Oct 2024
- 2024TeachTune: Reviewing Pedagogical Agents Against Diverse Student Profiles with Simulated Students5 Oct 2024
- 2024Students' Perceived Roles, Opportunities, and Challenges of a Generative AI-powered Teachable Agent: A Case of Middle School Math Class26 Aug 2024
- 2024Psychometric Alignment: Capturing Human Knowledge Distributions via Language Models22 Jul 2024
- 2024Generative Students: Using LLM-Simulated Student Profiles to Support Question Item Evaluation19 May 2024
- 2024Evaluating and Optimizing Educational Content with Large Language Model Judgments5 Mar 2024
- 2025LLM Agents for Education: Advances and Applicationscited by 59
- 2024TeachTune: Reviewing Pedagogical Agents Against Diverse Student Profiles with Simulated Studentscited by 25
- 2025Training Turn-by-Turn Verifiers for Dialogue Tutoring Agents: The Curious Case of LLMs as Your Coding Tutorscited by 17
- 2025Classroom Simulacra: Building Contextual Student Generative Agents in Online Education for Learning Behavioral Simulationcited by 15
- 2026How AI Coding Agents Modify Code: A Large-Scale Study of GitHub Pull Requestscited by 7
- 2026DiLLS: Interactive Diagnosis of LLM-based Multi-agent Systems via Layered Summary of Agent Behaviorscited by 7
- 2025CodeEdu: A Multi-Agent Collaborative Platform for Personalized Coding Educationcited by 4
- 2025Carbon and Silicon, Coexist or Compete? A Survey on Human-AI Interactions in Agent-based Modeling and Simulationcited by 3
- 2025Evolution in Simulation: AI-Agent School with Dual Memory for High-Fidelity Educational Dynamicscited by 3
- 2025Feed-O-Meter: Investigating AI-Generated Mentee Personas as Interactive Agents for Scaffolding Design Feedback Practicecited by 0
- 2025Chrysalis: A Unified System for Comparing Active Teaching and Passive Learning with AI Agents in Educationcited by 0
- 2025Student Development Agent: Risk-free Simulation for Evaluating AIED Innovationscited by 0
12 most cited of 17 All 17 (JSON)
- 2026Oops, Not Now: PEARL, a RAG-Based Support Agent for Gameplay and What Players Want from AI Help12 Sep 2026
- 2026In-IDE Toolkit for Developers of AI-Based Features14 May 2026
- 2026CPEMH: An Agentic Framework for Prompt-Driven Behavior Evaluation and Assurance in Foundation-Model Systems for Mental Health Screening11 May 2026
- 2026DiLLS: Interactive Diagnosis of LLM-based Multi-agent Systems via Layered Summary of Agent Behaviors5 Feb 2026
- 2026How AI Coding Agents Modify Code: A Large-Scale Study of GitHub Pull Requests24 Jan 2026
- 2025Argus: A Multi-Agent Sensitive Information Leakage Detection Framework Based on Hierarchical Reference Relationships9 Dec 2025
- 2025Evolution in Simulation: AI-Agent School with Dual Memory for High-Fidelity Educational Dynamics13 Oct 2025
- 2025DebugTA: An LLM-Based Agent for Simplifying Debugging and Teaching in Programming Education13 Oct 2025
- 2025Student Development Agent: Risk-free Simulation for Evaluating AIED Innovations10 Oct 2025
- 2025Chrysalis: A Unified System for Comparing Active Teaching and Passive Learning with AI Agents in Education6 Oct 2025
- 2025Feed-O-Meter: Investigating AI-Generated Mentee Personas as Interactive Agents for Scaffolding Design Feedback Practice9 Sep 2025
- 2025CodeEdu: A Multi-Agent Collaborative Platform for Personalized Coding Education18 Jul 2025
12 newest of 17 All 17 (JSON)
- 2024Generative Students: Using LLM-Simulated Student Profiles to Support Question Item Evaluationcited by 56
- 2024CodeXEmbed: A Generalist Embedding Model Family for Multiligual and Multi-task Code Retrievalcited by 33
- 2025SweRank: Software Issue Localization with Code Rankingcited by 20
- 2024Psychometric Alignment: Capturing Human Knowledge Distributions via Language Modelscited by 18
- 2025Understanding the LLM-ification of CHI: Unpacking the Impact of LLMs at CHI through a Systematic Literature Reviewcited by 16
- 2026Simulated Students in Tutoring Dialogues: Substance or Illusion?cited by 14
- 2024Beyond the Hype: A Comprehensive Review of Current Trends in Generative AI Research, Teaching Practices, and Toolscited by 13
- 2024Large Language Models in Computer Science Education: A Systematic Literature Reviewcited by 12
- 2026When and What to Ask: AskBench and Rubric-Guided RLVR for LLM Clarificationcited by 12
- 2024Evaluating and Optimizing Educational Content with Large Language Model Judgmentscited by 11
- 2025The StudyChat Dataset: Analyzing Student Dialogues With ChatGPT in an Artificial Intelligence Coursecited by 7
- 2026Towards Valid Student Simulation with Large Language Modelscited by 7
12 most cited of 19 All 19 (JSON)
- 2026KnowSim: Evaluating Information Calibration in LLM Assistants with User Simulators that Learn17 Aug 2026
- 2026Interpretable Difficulty-Aware Knowledge Tracing in Tutor-Student Dialogues1 May 2026
- 2026The RIGID Framework: Research-Integrated, Generative AI-Mediated Instructional Design13 Mar 2026
- 2026When and What to Ask: AskBench and Rubric-Guided RLVR for LLM Clarification4 Feb 2026
- 2026Human-Human-AI Triadic Programming: Uncovering the Role of AI Agent and the Value of Human Partner in Collaborative Learning17 Jan 2026
- 2026Towards Valid Student Simulation with Large Language Models9 Jan 2026
- 2026Simulated Students in Tutoring Dialogues: Substance or Illusion?7 Jan 2026
- 2025Beyond prior knowledge: The predictive role of knowledge-building in Tutor Learning25 Aug 2025
- 2025SweRank: Software Issue Localization with Code Ranking7 May 2025
- 2025Synthesizing High-Quality Programming Tasks with LLM-based Expert and Student Agents10 Apr 2025
- 2025The StudyChat Dataset: Analyzing Student Dialogues With ChatGPT in an Artificial Intelligence Course11 Mar 2025
- 2025Understanding the LLM-ification of CHI: Unpacking the Impact of LLMs at CHI through a Systematic Literature Review22 Jan 2025
12 newest of 19 All 19 (JSON)
Similar, not cited
Close in wording, no citation either way
- 2023Can Language Models Teach Weaker Agents? Teacher Explanations Improve Students via Personalization
- 2025EducationQ: Evaluating LLMs' Teaching Capabilities Through Multi-Agent Dialogue Framework
- 2025Enabling Multi-Agent Systems as Learning Designers: Applying Learning Sciences to AI Instructional Design
- 2023AgentTuning: Enabling Generalized Agent Abilities for LLMs
- 2023ChatLogo: A Large Language Model-Driven Hybrid Natural-Programming Language Interface for Agent-based Modeling and Programming
- 2024Ruffle&Riley: Insights from Designing and Evaluating a Large Language Model-Based Conversational Tutoring System
- 2025CoDAE: Adapting Large Language Models for Education via Chain-of-Thought Data Augmentation
- 2025A Theory of Adaptive Scaffolding for LLM-Based Pedagogical Agents