LearnMate^2: Design and Evaluation of an LLM-powered Personalized and Adaptive Support System for Online Learning

2026-05-07

AI Summary

This study addresses the pervasive lack of personalized guidance in online learning, which often fails to meet individual learners’ needs. To overcome this limitation, the authors propose an adaptive learning support system that integrates large language models (LLMs) with sound educational design principles. The system delivers deep personalization through customized learning plans, real-time contextual support, and dynamically adjusted learning activities. It synergistically combines LLM capabilities, adaptive algorithms, and an iterative human-centered interaction design, validated through user studies. Experimental results demonstrate that the proposed system significantly outperforms both conventional online learning platforms and generic LLM-based assistance tools in terms of learning effectiveness and user experience, offering a robust and effective paradigm for AI-driven personalized education.

Abstract

Personalization is crucial for effective learning, yet online learning, designed for widespread availability and open access, lacks personalized guidance. Recent advancements in large language models (LLMs) offer opportunities to bridge this gap. We explore how LLM-driven tools may be designed to support personalized and adaptive learning and examine how they shape user experience and learning outcomes. We iteratively designed \tool{} to support online learning by providing personalized study plans, real-time contextual assistance, and adaptive learning activities. A preliminary study ($n=24$) assessed the effectiveness and usability of \tool{} and informed refinements in our system, which we then evaluated ($n = 16$) against a combination of a state-of-the-art online learning platform and an LLM for learning support. Results indicate that \tool{} advances AI pedagogy by improving both learning outcomes and user experience compared to existing online learning and support tools. This work advances our understanding of the design space of personalized, AI-driven educational tools and their potential impact on user experience.

Problem

• personalization
• online learning
• adaptive support
• AI-driven education
• learning guidance

Innovation

• personalized learning
• adaptive support
• large language models
• AI pedagogy
• online learning