Intelligent Learning Architecture: Designing an AI-Based Adaptive Learning Model to Enhance Students’ Self-Regulation, Academic Engagement, and Achievement

Abstract

The rapid development of artificial intelligence has created new opportunities for schools to move beyond standardized instruction toward personalized learning. This proposed study aims to design and evaluate an AI-based adaptive learning model intended to improve students’ academic self-regulation, engagement, and educational achievement. Within the proposed model, content difficulty, feedback type, instructional pace, and learning pathways will be adjusted according to each student’s performance, needs, and behavioral patterns. A mixed-methods design will be employed in two phases: model development and effectiveness evaluation. The quantitative phase will compare students receiving adaptive AI-supported instruction with those receiving conventional instruction, while the qualitative phase will explore students’ and teachers’ experiences regarding effectiveness, fairness, usability, and implementation challenges. The proposed model is expected to strengthen learner autonomy, reduce educational gaps, and promote more meaningful student participation in the learning process.