Personalized Parsons Puzzles as Scaffolding Enhance Practice Engagement Over Just Showing LLM-Powered Solutions
Xinying Hou, Zihan Wu, Xu Wang, Barbara J. Ericson
TL;DR
The paper addresses the risk that AI-assisted coding can dampen learning by providing ready-made answers. It evaluates a scaffolded approach using personalized Parsons puzzles versus complete AI-generated solutions in a Python practice setting through a randomized classroom study. The results indicate that puzzle-based scaffolding substantially increases practice engagement compared with full solutions, suggesting that active, puzzle-driven scaffolding promotes deeper engagement with programming tasks. This work supports incorporating targeted, interactive scaffolds in AI-assisted programming education to foster sustained practice and learning gains in real classroom environments.
Abstract
As generative AI products could generate code and assist students with programming learning seamlessly, integrating AI into programming education contexts has driven much attention. However, one emerging concern is that students might get answers without learning from the LLM-generated content. In this work, we deployed the LLM-powered personalized Parsons puzzles as scaffolding to write-code practice in a Python learning classroom (PC condition) and conducted an 80-minute randomized between-subjects study. Both conditions received the same practice problems. The only difference was that when requesting help, the control condition showed students a complete solution (CC condition), simulating the most traditional LLM output. Results indicated that students who received personalized Parsons puzzles as scaffolding engaged in practicing significantly longer than those who received complete solutions when struggling.