Gu, R., Zhang, J., Miguel Rojas, J. et al. (1 more author) (Accepted: 2025) On the promises and challenges of AI-powered XR glasses as embodied software. In: Proceedings of the 2nd ACM International Conference on AI-Powered Software. 2nd ACM International Conference on AI-Powered Software (AIware 2025), 19-20 Nov 2025, Seoul, South Korea. Association for Computing Machinery (ACM). (In Press)
Abstract
AI-powered Extended Reality (XR) glasses represent the next frontier in software interface, integrating spatial computing with foundation models (FMs) to interact with physical environments in real-time. This technology promises a rich, immersive, and interactive user experience with seamless integration in real-world scenarios, while simultaneously introducing unprecedented challenges at the intersection of AI and Software Engineering (SE). This vision paper aims to catalyse the development of robust spatial software by characterising XR glasses as a distinct software paradigm through a conceptual framework and defining its advanced capabilities. We identify critical research problems, including security and privacy, validation of spatial capabilities, and explainability, while highlighting broader societal implications spanning ethics, accessibility, inclusivity, and open development ecosystems. Finally, we outline pathways for developing reliable and trustworthy XR systems in the FM era.
Metadata
| Item Type: | Proceedings Paper |
|---|---|
| Authors/Creators: |
|
| Copyright, Publisher and Additional Information: | © 2025 ACM. |
| Keywords: | AI-powered XR glasses; embodied AI; extended reality; human-AI collaboration; security and privacy; spatial intelligence |
| Dates: |
|
| Institution: | The University of Sheffield |
| Academic Units: | The University of Sheffield > Faculty of Engineering (Sheffield) > Department of Computer Science (Sheffield) |
| Funding Information: | Funder Grant number ENGINEERING AND PHYSICAL SCIENCE RESEARCH COUNCIL EP/Y014219/1 |
| Date Deposited: | 05 Nov 2025 16:29 |
| Last Modified: | 05 Nov 2025 16:33 |
| Status: | In Press |
| Publisher: | Association for Computing Machinery (ACM) |
| Refereed: | Yes |
| Related URLs: | |
| Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:233948 |
Download
Filename: AIware_2025.pdf

CORE (COnnecting REpositories)
CORE (COnnecting REpositories)