Owlgorithm: Supporting Self-Regulated Learning in Competitive Programming through LLM-Driven Reflection

TL;DR

Owlgorithm is an educational platform that uses GPT-4o to generate personalized reflective questions, supporting self-regulated learning in competitive programming by guiding students through reflection and debugging.

Contribution

It introduces a novel AI-driven approach to facilitate metacognitive reflection in competitive programming education, with adaptive prompts tailored to student performance.

Findings

Students found generated questions useful for reflection and debugging

Feedback accuracy and usability pose challenges for classroom integration

AI-supported reflection benefits novice programmers but needs refinement for advanced learners

Abstract

We present Owlgorithm, an educational platform that supports Self-Regulated Learning (SRL) in competitive programming (CP) through AI-generated reflective questions. Leveraging GPT-4o, Owlgorithm produces context-aware, metacognitive prompts tailored to individual student submissions. Integrated into a second- and third-year CP course, the system-provided reflective prompts adapted to student outcomes: guiding deeper conceptual insight for correct solutions and structured debugging for partial or failed ones. Our exploratory assessment of student ratings and TA feedback revealed both promising benefits and notable limitations. While many found the generated questions useful for reflection and debugging, concerns were raised about feedback accuracy and classroom usability. These results suggest advantages of LLM-supported reflection for novice programmers, though refinements are needed to ensure reliability and pedagogical value for advanced learners. From our experience, several key insights emerged: GenAI can effectively support structured reflection, but careful prompt design, dynamic adaptation, and usability improvements are critical to realizing their potential in education. We offer specific recommendations for educators using similar tools and outline next steps to enhance Owlgorithm's educational impact. The underlying framework may also generalize to other reflective learning contexts.