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

Süleyman Özdel, Technical University of Munich

Can Sarpkaya, Technical University of Munich

Efe Bozkir, Technical University of Munich

Hong Gao, Soochow University

Enkelejda Kasneci, Technical University of Munich

Date

05/2025

AI Overview

Why it matters

Individualized virtual learning often lacks collaborative peer interactions. The effects of integrating large language model interactions into virtual reality classrooms on student engagement and attention remain open questions.

Study at a glance

Question: How do AI peer questions affect student attention, cognitive load, and learning outcomes in a virtual reality classroom?
Setting and data: 19 adult participants (mean age 25.32 years) in a virtual reality classroom experiment, Germany; dates not stated.
Method: Within-subjects experiment with counterbalanced topic order, paired with eye tracking, cognitive load tests, and questionnaires.
AI tools: ChatGPT-4o, Whisper API, Amazon Polly

Key findings

In a complex physics lesson, AI peer questions significantly increased participants' cognitive load scores and pupil diameters, which strongly correlated with visual attention on instructional content.
Peer questions directed visual attention more precisely toward instructional content during the complex lesson, producing significantly longer fixation durations and shorter saccade amplitudes.
Knowledge test scores did not differ significantly between conditions, but shorter saccade durations were significantly associated with higher test scores in the complex lesson.

Summary drafted with AI from the full paper and may contain errors. See the full paper for details.

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.