OnlineMate: An LLM-Based Multi-Agent Companion System for Cognitive Support in Online Learning

2025-09-18

AI Summary

In online learning, students frequently lack personalized peer interaction, resulting in insufficient cognitive engagement and constrained deep learning. Existing LLM-based learning companions support only unidirectional dialogue and cannot reliably infer or adapt to learners’ cognitive states (e.g., misconceptions, confusion) or motivational factors. To address this, we propose a Theory of Mind (ToM)-enhanced multi-agent collaborative framework that leverages large language models to instantiate an AI learning companion ensemble capable of dynamic learner state modeling and context-aware, adaptive interaction strategy generation. Experimental results demonstrate statistically significant improvements in discussion depth, cognitive engagement, and higher-order thinking performance. Our approach provides a scalable, cognitively grounded technical pathway for personalized metacognitive support in digital learning environments.

Technology Category

• Multiagent Systems: Multiagent Learning
• Machine Learning: Large Multimodal Models (LMMs)
• Cognitive Modeling & Cognitive Systems: Adaptive Behavior

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

In online learning environments, students often lack personalized peer interactions, which play a crucial role in supporting cognitive development and learning engagement. Although previous studies have utilized large language models (LLMs) to simulate interactive dynamic learning environments for students, these interactions remain limited to conversational exchanges, lacking insights and adaptations to the learners' individualized learning and cognitive states. As a result, students' interest in discussions with AI learning companions is low, and they struggle to gain inspiration from such interactions. To address this challenge, we propose OnlineMate, a multi-agent learning companion system driven by LLMs that integrates the Theory of Mind (ToM). OnlineMate is capable of simulating peer-like agent roles, adapting to learners' cognitive states during collaborative discussions, and inferring their psychological states, such as misunderstandings, confusion, or motivation. By incorporating Theory of Mind capabilities, the system can dynamically adjust its interaction strategies to support the development of higher-order thinking and cognition. Experimental results in simulated learning scenarios demonstrate that OnlineMate effectively fosters deep learning and discussions while enhancing cognitive engagement in online educational settings.

Problem

• Simulates peer-like agent roles for cognitive support
• Adapts to learners' cognitive states during discussions
• Infer psychological states to adjust interaction strategies

Innovation

• LLM-based multi-agent system with Theory of Mind
• Adapts to learners' cognitive states dynamically
• Simulates peer roles for enhanced engagement