A Benchmarking Framework for Context-aware XR Interfaces

2026-09-24

AI Summary

This study addresses the absence of systematic evaluation methodologies for context-aware XR interfaces by proposing ContextXR, a novel benchmarking framework. The framework introduces functional facet graph modeling to abstract XR applications into graph structures and constructs MineXR++, an augmented dataset that defines three categories of recommendation tasks. Furthermore, it establishes a quantitative evaluation protocol incorporating simulated interaction and navigation search costs. Leveraging this framework, the authors conduct systematic and reproducible benchmark comparisons across adaptation methods, including global popularity, relational retrieval, and large language models (LLMs). By providing a standardized assessment paradigm, this work effectively fills a critical gap in the rigorous evaluation of context-aware XR systems.

Abstract

Everyday Extended Reality (XR) systems aim to provide context-aware access to the right functionalities at the right time and place, with minimal manual reconfiguration as users switch context. Yet these interfaces are hard to evaluate: current prototyping and user-study workflows offer no systematic, repeatable way to compare adaptation methods across users and scenarios. We present ContextXR, a novel benchmarking framework for context-aware XR interfaces. ContextXR represents an XR application as a connected graph of functional facets, each a semantically coherent group of related capabilities that together support a shared user intent. On this representation, we build MineXR++, a dataset augmenting prior XR interface data with facet-level annotations, and formulate three canonical tasks of context-aware suggestion: context factor analysis, initial facet suggestion, and next facet suggestion. Our evaluation protocol scores suggestion methods by a simulated interaction metric, the navigation and search cost of reaching the desired functionality. Through experiments benchmarking global popularity, relational retrieval, and LLM-based methods, we demonstrate that ContextXR enables the systematic, reproducible evaluation of context-aware XR interfaces.

Problem

• Extended Reality
• Context-aware Interfaces
• Benchmarking
• Evaluation

Innovation

• Context-aware XR
• Benchmarking framework
• Functional facets graph
• Dataset augmentation
• LLM-based suggestion