MRGEN: A Conceptual Framework for LLM-Powered Mixed Reality Authoring Tools for Education

TL;DR

MRGEN is a framework leveraging LLMs to simplify the creation of educational mixed reality content on mobile devices, demonstrated through a prototype that improved efficiency and user satisfaction.

Contribution

This paper introduces MRGEN, a novel conceptual framework integrating LLMs into MR authoring tools for education, validated by a prototype and user study.

Findings

LLM-powered authoring reduced task duration by 36%.

Over 90% of participants found AI support helpful.

The framework shows promise for future AI-assisted MR tools.

Abstract

Mixed Reality (MR) offers immersive and multimodal opportunities for education but remains difficult for teachers to author without technical expertise. We propose MRGEN, a conceptual framework for LLM-powered authoring tools to support teachers in creating MR learning activities that work on mobile devices (tablets and smartphones). MRGEN articulates three axes: Learning Objectives, MR Modality, and GAI Assistance. To validate our framework, we implemented a prototype based on the open-source MIXAP authoring platform and conducted a user study with 24 participants. Results show that LLM-powered authoring reduced task duration by 36% on average, and that over 90% of participants found the AI support helpful for brainstorming, structuring, and aligning content with their learning goals. These findings yielded very promising results for future AI-assisted MR authoring tools.