# CodeTailor: LLM-Powered Personalized Parsons Puzzles for Engaging Support While Learning Programming

arXiv: https://arxiv.org/abs/2401.12125 · HTML: https://mlsanity.com/paper/2401.12125/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Jan 2024.

## Built on by (most cited first, 11 of 11)

- [Exploring the Design Space of Cognitive Engagement Techniques with AI-Generated Code for Enhanced Learning](https://mlsanity.com/paper/2410.08922/) (2024)
- [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)
- [Insights from Social Shaping Theory: The Appropriation of Large Language Models in an Undergraduate Programming Course](https://mlsanity.com/paper/2406.06451/) (2024)
- [Improving Student-AI Interaction Through Pedagogical Prompting: An Example in Computer Science Education](https://mlsanity.com/paper/2506.19107/) (2025)
- [Personalized Worked Example Generation from Student Code Submissions Using Pattern-based Knowledge Components](https://mlsanity.com/paper/2604.24758/) (2026)
- [Exploring Teacher-Chatbot Interaction and Affect in Block-Based Programming](https://mlsanity.com/paper/2603.20211/) (2026)
- [Exploring Student Choice and the Use of Multimodal Generative AI in Programming Learning](https://mlsanity.com/paper/2510.05417/) (2025)
- [Leveraging Test Driven Development with Large Language Models for Reliable and Verifiable Spreadsheet Code Generation: A Research Framework](https://mlsanity.com/paper/2510.15585/) (2025)
- [From Pilots to Practices: A Scoping Review of GenAI-Enabled Personalization in Computer Science Education](https://mlsanity.com/paper/2512.20714/) (2025)
- [TutorTrace: A Dataset and Taxonomy for Classifying Learner Behavioral States during AI-Assisted Programming Education](https://mlsanity.com/paper/2608.26184/) (2026)

## Abstract (arXiv)

Learning to program can be challenging, and providing high-quality and timely support at scale is hard. Generative AI and its products, like ChatGPT, can create a solution for most intro-level programming problems. However, students might use these tools to just generate code for them, resulting in reduced engagement and limited learning. In this paper, we present CodeTailor, a system that leverages a large language model (LLM) to provide personalized help to students while still encouraging cognitive engagement. CodeTailor provides a personalized Parsons puzzle to support struggling students. In a Parsons puzzle, students place mixed-up code blocks in the correct order to solve a problem. A technical evaluation with previous incorrect student code snippets demonstrated that CodeTailor could deliver high-quality (correct, personalized, and concise) Parsons puzzles based on their incorrect code. We conducted a within-subjects study with 18 novice programmers. Participants perceived CodeTailor as more engaging than just receiving an LLM-generated solution (the baseline condition). In addition, participants applied more supported elements from the scaffolded practice to the posttest when using CodeTailor than baseline. Overall, most participants preferred using CodeTailor versus just receiving the LLM-generated code for learning. Qualitative observations and interviews also provided evidence for the benefits of CodeTailor, including thinking more about solution construction, fostering continuity in learning, promoting reflection, and boosting confidence. We suggest future design ideas to facilitate active learning opportunities with generative AI techniques.