Examining the Role of LLM-Driven Interactions on Attention and Cognitive Engagement in Virtual Classrooms

2025-05-12

AI Summary

This study investigates how AI peer questioning behaviors in LLM-driven virtual classrooms affect students’ attention, cognitive load, and learning outcomes. We developed a fully LLM-powered VR instructional environment integrated with eye-tracking, subjective cognitive load measurement (Paas scale), and multimodal learning behavior analytics. Results demonstrate that structured AI peer questioning significantly enhances visual attentional focus on core instructional content—improving attentional allocation without increasing extraneous cognitive load. Furthermore, cognitive load correlates positively with attention to learning materials, indicating it reflects productive cognitive engagement rather than redundant processing. The study identifies AI peers as critical regulators of learners’ attentional resources in immersive environments and proposes evidence-based design principles for cognitively optimized VR educational spaces. These findings advance theoretical understanding of AI-mediated attention regulation and provide actionable guidelines for developing effective, LLM-augmented immersive learning systems.

Technology Category

• Humans and AI: Game Design — Virtual Humans, NPCs and Autonomous Characters
• Machine Learning: Large Multimodal Models (LMMs)
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior

Application Category

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

Abstract

Transforming educational technologies through the integration of large language models (LLMs) and virtual reality (VR) offers the potential for immersive and interactive learning experiences. However, the effects of LLMs on user engagement and attention in educational environments remain open questions. In this study, we utilized a fully LLM-driven virtual learning environment, where peers and teachers were LLM-driven, to examine how students behaved in such settings. Specifically, we investigate how peer question-asking behaviors influenced student engagement, attention, cognitive load, and learning outcomes and found that, in conditions where LLM-driven peer learners asked questions, students exhibited more targeted visual scanpaths, with their attention directed toward the learning content, particularly in complex subjects. Our results suggest that peer questions did not introduce extraneous cognitive load directly, as the cognitive load is strongly correlated with increased attention to the learning material. Considering these findings, we provide design recommendations for optimizing VR learning spaces.

Problem

• Effects of LLMs on engagement in virtual classrooms
• Impact of peer questions on student attention
• Cognitive load correlation with learning material focus

Innovation

• LLM-driven virtual learning environment
• Peer question-asking boosts engagement
• VR optimized via attention metrics