IllusionX: An LLM-powered mixed reality personal companion
Ramez Yousri, Zeyad Essam, Yehia Kareem, Youstina Sherief, Sherry Gamil, Soha Safwat
TL;DR
The paper addresses building a personalized educational assistant by integrating LLMs, mixed reality, and affective computing. It introduces IllusionX, a modular system combining a PaLM2-based LLM backend, a FastAPI/PostgreSQL API, a Flutter mobile app, and AR glasses with a smartwatch to deliver information retrieval, tutoring, and task support in an immersive interface. Technology-adoption surveys and targeted educational tasks with knowledge embedding show improved coherence and more technical Q&A, but performance remains constrained by the documents provided and the risk of hallucination. The work highlights ethical considerations and outlines future directions to enhance robustness, multilingual/multimodal capabilities, and hardware advances for broader educational impact.
Abstract
Mixed Reality (MR) and Artificial Intelligence (AI) are increasingly becoming integral parts of our daily lives. Their applications range in fields from healthcare to education to entertainment. MR has opened a new frontier for such fields as well as new methods of enhancing user engagement. In this paper, We propose a new system one that combines the power of Large Language Models (LLMs) and mixed reality (MR) to provide a personalized companion for educational purposes. We present an overview of its structure and components as well tests to measure its performance. We found that our system is better in generating coherent information, however it's rather limited by the documents provided to it. This interdisciplinary approach aims to provide a better user experience and enhance user engagement. The user can interact with the system through a custom-design smart watch, smart glasses and a mobile app.