Design of AI-Powered Tool for Self-Regulation Support in Programming Education
Huiyong Li, Boxuan Ma
TL;DR
The paper addresses the mismatch between stand-alone AI programming assistants and institutional LMS contexts, and the need to cultivate self-regulated learning (SRL) in introductory programming. It introduces CodeRunner Agent, an LLM-based tool integrated with the Moodle CodeRunner plugin, utilizing a dual-context system (LACE and KCE) to deliver context-aware, strategy-based feedback drawn from lecture materials, questions, student answers, and execution results. The approach operationalizes Zimmerman's SRL framework through the PPESS five-phase model (Planning, Program creation, Error correction, Self-monitoring, Self-reflection) and logs interactions via xAPI for data-driven evaluation. The work aims to enable data-driven improvements in programming education by tightly coupling AI feedback with course materials and SRL scaffolding, while providing educators with scalable, context-rich analytics.
Abstract
Large Language Model (LLM) tools have demonstrated their potential to deliver high-quality assistance by providing instant, personalized feedback that is crucial for effective programming education. However, many of these tools operate independently from institutional Learning Management Systems, which creates a significant disconnect. This isolation limits the ability to leverage learning materials and exercise context for generating tailored, context-aware feedback. Furthermore, previous research on self-regulated learning and LLM support mainly focused on knowledge acquisition, not the development of important self-regulation skills. To address these challenges, we developed CodeRunner Agent, an LLM-based programming assistant that integrates the CodeRunner, a student-submitted code executing and automated grading plugin in Moodle. CodeRunner Agent empowers educators to customize AI-generated feedback by incorporating detailed context from lecture materials, programming questions, student answers, and execution results. Additionally, it enhances students' self-regulated learning by providing strategy-based AI responses. This integrated, context-aware, and skill-focused approach offers promising avenues for data-driven improvements in programming education.