Daniel Platnick, Matti Gruener, Marjan Alirezaie, Kent Larson, Dava J. Newman and Hossein Rahnama

Abstract

AI-enhanced Extended Reality (XR) aims to deliver adaptive, immersive experiences, yet current systems fall short due to shallow user modeling and limited cognitive context. We introduce Perspective-Aware AI in Extended Reality (PAiR), a foundational framework that integrates Perspective-Aware AI (PAi) with XR to enable interpretable, context-aware interactions grounded in user identity. PAi is built on Chronicles—reasoning-ready identity models derived from multimodal digital footprints that capture users’ cognitive and experiential evolution. PAiR employs these models in a closed-loop system linking dynamic user states with immersive environments. We present PAiR’s architecture, detailing its modules and system flow, and demonstrate its utility through two proof-of-concept scenarios implemented in the Unity-based OpenDome engine. PAiR opens a new direction for human-AI interaction by embedding perspective-driven identity into immersive systems.