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

Created: 2026-05-15 | Tags: personalized-learningadaptive-learningllmgenerative-aihigher-edscaffolding

LearnMate^2: Design and Evaluation of an LLM-powered Personalized and Adaptive Support System for Online Learning Wang, Lee, & Mutlu (2026) โ€” University of Wisconsin-Madison. CHI-related publication. ๐Ÿ“„ Full text (arXiv)

Summary

LearnMate^2 addresses the personalization gap in online learning: while online platforms offer widespread access, they lack the personalized guidance that characterizes effective intelligent-tutoring systems. The system provides three core capabilities:

1. Personalized study plans โ€” tailored learning paths based on individual learner profiles 2. Real-time contextual assistance โ€” in-context support during learning sessions via conversational-ai-tutors-framework 3. Adaptive learning activities โ€” dynamic tasks responding to learner performance, implementing adaptive-learning-systems principles

Iterative development and evaluation:

The study demonstrates that LLM-powered personalized-learning can bridge the guidance gap in open online education. This connects to the broader adaptive-learning-systems literature and extends findings from learnmate2-llm-adaptive-learning prior iterations. The system's integration of study planning, real-time assistance, and adaptive activities represents a more holistic approach than single-function AI tools, aligning with the agentic-ai-ecosystems-higher-education vision of integrated educational AI.

The work also contributes to understanding how scaffolding can be implemented at scale in digital environments, complementing ai-metacognition-stem-review findings on metacognitive support tools.

Related Pages

Citation

APA: Wang, X. J., Lee, C. P., & Mutlu, B. (2026). LearnMate^2: Design and evaluation of an LLM-powered personalized and adaptive support system for online learning. arXiv:2605.06257. https://doi.org/10.1145/3800645.3812972