# How to Teach Programming in the AI Era? Using LLMs as a Teachable Agent for Debugging

arXiv: https://arxiv.org/abs/2310.05292 · HTML: https://mlsanity.com/paper/2310.05292/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 7 of its 31 references that are in the map.
- First posted on arXiv 8 Oct 2023.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 7 of 7)

- [AI Chains: Transparent and Controllable Human-AI Interaction by Chaining Large Language Model Prompts](https://mlsanity.com/paper/2110.01691/) (2021)
- [Predictability and Surprise in Large Generative Models](https://mlsanity.com/paper/2202.07785/) (2022)
- [GitHub Copilot AI pair programmer: Asset or Liability?](https://mlsanity.com/paper/2206.15331/) (2022)
- [Programming Is Hard -- Or at Least It Used to Be: Educational Opportunities And Challenges of AI Code Generation](https://mlsanity.com/paper/2212.01020/) (2022)
- [Reading Between the Lines: Modeling User Behavior and Costs in AI-Assisted Programming](https://mlsanity.com/paper/2210.14306/) (2022)
- [Thrilled by Your Progress! Large Language Models (GPT-4) No Longer Struggle to Pass Assessments in Higher Education Programming Courses](https://mlsanity.com/paper/2306.10073/) (2023)
- [Is AI the better programming partner? Human-Human Pair Programming vs. Human-AI pAIr Programming](https://mlsanity.com/paper/2306.05153/) (2023)

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

- [LLM Agents for Education: Advances and Applications](https://mlsanity.com/paper/2503.11733/) (2025)
- [Exploring Knowledge Tracing in Tutor-Student Dialogues using LLMs](https://mlsanity.com/paper/2409.16490/) (2024)
- [What Should We Engineer in Prompts? Training Humans in Requirement-Driven LLM Use](https://mlsanity.com/paper/2409.08775/) (2024)
- [AI-TA: Towards an Intelligent Question-Answer Teaching Assistant using Open-Source LLMs](https://mlsanity.com/paper/2311.02775/) (2023)
- [Position: Towards Bidirectional Human-AI Alignment](https://mlsanity.com/paper/2406.09264/) (2024)
- [Large Language Models in Computer Science Education: A Systematic Literature Review](https://mlsanity.com/paper/2410.16349/) (2024)
- [Combining Large Language Models with Tutoring System Intelligence: A Case Study in Caregiver Homework Support](https://mlsanity.com/paper/2412.11995/) (2024)
- [SPHERE: An Evaluation Card for Human-AI Systems](https://mlsanity.com/paper/2504.07971/) (2025)
- [Towards Valid Student Simulation with Large Language Models](https://mlsanity.com/paper/2601.05473/) (2026)
- [The Evolution of LLM Adoption in Industry Data Curation Practices](https://mlsanity.com/paper/2412.16089/) (2024)
- [Beyond One-Way Influence: Bidirectional Opinion Dynamics in Multi-Turn Human-LLM Interactions](https://mlsanity.com/paper/2510.20039/) (2025)
- [BugSpotter: Automated Generation of Code Debugging Exercises](https://mlsanity.com/paper/2411.14303/) (2024)
- [When Models Know More Than They Can Explain: Quantifying Knowledge Transfer in Human-AI Collaboration](https://mlsanity.com/paper/2506.05579/) (2025)
- [Synthesizing High-Quality Programming Tasks with LLM-based Expert and Student Agents](https://mlsanity.com/paper/2504.07655/) (2025)
- [From Untamed Black Box to Interpretable Pedagogical Orchestration: The Ensemble of Specialized LLMs Architecture for Adaptive Tutoring](https://mlsanity.com/paper/2603.23990/) (2026)
- [Simulating Novice Students Using Machine Unlearning and Relearning in Large Language Models](https://mlsanity.com/paper/2603.26142/) (2026)
- [InstructPipe: Generating Visual Blocks Pipelines with Human Instructions and LLMs](https://mlsanity.com/paper/2312.09672/) (2023)
- [Prompt Programming: A Platform for Dialogue-based Computational Problem Solving with Generative AI Models](https://mlsanity.com/paper/2503.04267/) (2025)
- [Dialogic Pedagogy for Large Language Models: Aligning Conversational AI with Proven Theories of Learning](https://mlsanity.com/paper/2506.19484/) (2025)
- [Designing Conversational AI to Support Think-Aloud Practice in Technical Interview Preparation for CS Students](https://mlsanity.com/paper/2507.14418/) (2025)
- [The promise and limits of LLMs in constructing proofs and hints for logic problems in intelligent tutoring systems](https://mlsanity.com/paper/2505.04736/) (2025)
- [CogGen: A Learner-Centered Generative AI Architecture for Intelligent Tutoring with Programming Video](https://mlsanity.com/paper/2506.20600/) (2025)
- [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)
- [Beyond prior knowledge: The predictive role of knowledge-building in Tutor Learning](https://mlsanity.com/paper/2508.18545/) (2025)
- [Designing and Evaluating Chain-of-Hints for Scientific Question Answering](https://mlsanity.com/paper/2510.21087/) (2025)
- [Assessing the Software Security Comprehension of Large Language Models](https://mlsanity.com/paper/2512.21238/) (2025)
- [Human-AI Interaction Alignment: Designing, Evaluating, and Evolving Value-Centered AI For Reciprocal Human-AI Futures](https://mlsanity.com/paper/2512.21551/) (2025)
- [Enhancing Debugging Skills with AI-Powered Assistance: A Real-Time Tool for Debugging Support](https://mlsanity.com/paper/2601.02504/) (2026)
- [Chat Debugging: An Exploratory Study of Human-AI Collaboration to Debug Analog Circuits](https://mlsanity.com/paper/2608.02955/) (2026)
- [Oops, Not Now: PEARL, a RAG-Based Support Agent for Gameplay and What Players Want from AI Help](https://mlsanity.com/paper/2609.13718/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) now excel at generative skills and can create content at impeccable speeds. However, they are imperfect and still make various mistakes. In a Computer Science education context, as these models are widely recognized as "AI pair programmers," it becomes increasingly important to train students on evaluating and debugging the LLM-generated code. 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.