RealityCraft: Automated Synthesis of Extended Reality Device Interaction Scripts from Natural Language Instructions
Shuqing Li, Yun Peng, Yige Chen, Dingyuan Xue, Yepang Liu, Michael R. Lyu
Abstract
Extended Reality (XR) apps have become increasingly popular across different domains, evidenced by its market growing to over $165 billion in 2024. Despite their widespread usage, XR apps present new challenges for automated software testing approaches, especially for testing script generation. XR apps have complicated action space from multi-device coordination with temporal precision. Besides, natural language instructions in XR apps usually have a large semantic gap with specific XR interactions. Therefore, previous testing script generation approaches on 2D apps such as Android can hardly be adopted into XR apps.
Ask about this paper
Ask your agent about it.
Lune has read the top-tier papers around this one, so every answer names the papers it rests on.
Related papers
- Look Before You Leap: Context-Sensitive GUI Grounding for Boosting Automated Extended Reality (XR) TestingShuqing Li, Binchang Li, Yepang Liu, Cuiyun Gao et al.FSE 2026
- XRFix: Exploring Performance Bug Repair of Extended Reality Applications with Large Language ModelsJingwen Wu, Hanyang Guo, Hong-Ning Dai, Xiapu LuoICSE 2026
- LLMER: Crafting Interactive Extended Reality Worlds with JSON Data Generated by Large Language ModelsJiangong Chen, Xiaoyi Wu, Tian Lan, Bin LiIEEE VR 2025 · 20 citations
- Demystifying Mobile Extended Reality in Web Browsers: How Far Can We Go?Weichen Bi, Yun Ma, Deyu Tian, Qi Yang et al.WWW 2023 · 5 citations
- Beyond the Phone: Exploring Phone-XR Integration through Multi-View Transitions for Real-World ApplicationsFengyuan Zhu, Xun Qian, Daniel Kalmar, Mahdi Tayarani et al.IEEE VR 2025 · 4 citations
