This project aims to develop an AI-powered adaptive programming learning system that personalizes coding exercises based on students’ proficiency and cognitive load. Grounded in Cognitive Load Theory (CLT) and powered by generative AI and retrieval-augmented generation (RAG), the platform dynamically adjusts the complexity of programming tasks, promoting efficient, engaging, and individualized learning. Addressing limitations in traditional programming education, the system continuously tracks learners’ behaviors, updates knowledge profiles, and generates exercises tailored to each student’s evolving capabilities.

The project’s objectives are to (1) improve student engagement and programming proficiency, (2) reduce cognitive overload, and (3) foster personalized, active learning environments in programming education. Deliverables include a fully functional adaptive learning platform, a validated RAG-based content generation system, and a peer-reviewed publication. By integrating cutting-edge AI with learning sciences, this initiative offers a scalable, data-driven model for transforming programming instruction across disciplines and learner levels.