LearnMate^2: Design and Evaluation of an LLM-powered Personalized and Adaptive Support System for Online Learning Wang, Lee, & Mutlu (2026) — University of Wisconsin-Madison. CHI-related publication.
LearnMate^2: Design and Evaluation of an LLM-powered Personalized and Adaptive Support System for Online Learning
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 — tailored learning paths based on individual learner profiles
2. Real-time contextual assistance — in-context support during learning sessions via Conversational AI Tutors Framework
3. Adaptive learning activities — dynamic tasks responding to learner performance, implementing Adaptive Learning principles
Iterative development and evaluation:
Preliminary study (n=24) assessed effectiveness, informed system refinementsComparative evaluation (n=16) against a state-of-the-art online learning platform plus an LLMResults: LearnMate^2 improved both learning outcomes and user experience vs. the baselineThe study demonstrates that LLM-powered Personalized Learning can bridge the guidance gap in open online education. This connects to the broader Adaptive Learning 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 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.
Connected Concepts
Adaptive LearningAgentic AIPersonalized LearningScaffoldingAdaptive LearningAgentic AIGenerative AIHigher EdLLMMetacognitionConnected Articles
AI Metacognition STEM Review — AI Tools Scaffolding Metacognition in STEMCodify Socratic Tutoring Programming — Codify: An Intelligent Socratic Tutoring System for Programming EducationConversational AI Tutors Framework — The Path to Conversational AI Tutors: Integrating Tutoring Best Practices and Targeted Technologies to Produce Scalab...A4l Analytics Pipeline — Generalizing a Highly Configurable Analytics Pipeline to Replicate and Support Educational Research Across Multiple D...Aaai2026 Prompting Literacy K12 — Learning to Use AI for Learning: Teaching Responsible Use of AI Chatbot to K-12 Students Through an AI Literacy ModuleAcademiclaw Student Agent Benchmark — AcademiClaw: When Students Set Challenges for AI AgentsAdapt Adaptive Lesson Plan Transformer — AdaPT: Adaptive Lesson Plan Transformer for Cross-Regional and Differentiated InstructionAdaptive Pretesting Retention — Do Gains from Generative AI-Enabled Adaptive Pretesting Persist? Evidence from a Retention StudyAffective Text Wearable Student Health — A Formative Study of Brief Affective Text as a Complement to Wearable Sensing for Longitudinal Student Health MonitoringAgency Gap AI Writing — The agency gap in AI-supported writing: how reactive and proactive agent designs shape multimodal reasoningAgent Voice Accents K12 Group Learning — Exploring How Agent Voice Accents Shape Human-AI Collaboration in K-12 Group LearningAgentic AI Education Scoping Review — Agentic AI in Education: A Scoping Review of Research Landscape, Capabilities, and the Frontier Agent ParadigmAgentic AI Pedagogical Best Practice 2026 — Agentic AI and Pedagogical Best Practice: The Tension Between Automation and LearningAgentic Education Coding — Agentic Education with AI Coding AssistantsAgentic Literacy Debt — Agentic Literacy Debt: A Structural Problem the AI Literacy Field Has Not Yet NamedAgentic Workflows Education — Agentic Workflows in EducationAgents That Teach Incidental Learning — Agents That Teach: Designing Incidental Learning Back into AI-Assisted Software DevelopmentAgreement Not Quality LLM Coding Verification — Agreement Is Not Quality: Blind Expert Verification of Human and LLM Qualitative Coding When Human Consensus Is Not G...AI Adult Learning Design — Guidelines for Designing AI Technologies to Support Adult LearningAI Adult Learning Guidelines Dis2026 — Guidelines for Designing AI Technologies to Support Adult LearningAI Agents Constructive Conflict Design Education 2026 — Enacting Constructive Conflicts with AI Agents to Enhance Reconsideration among Novice Interaction DesignersAI Agents Peer Learning Discourse — When AI Agents Teach Each Other: Discourse Patterns Resembling Peer Learning in the Moltbook CommunityAI Assessment Scale Reform — A bit of chaos and madness": The AI Assessment Scale and the work of assessment reformAI Assistance Discretionary Feedback — AI Assistance for Discretionary Work: Increasing Feedback Provision in Higher EducationAI Assisted Learning Modes Eeg — An exploratory behavioral and electroencephalographic study of artificial intelligence-assisted learning modes in hig...Citation
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