Vibe Coding XR: Accelerating AI + XR Prototyping with XR Blocks and Gemini

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Du, Ruofei, Hersh, Benjamin, Li, David, Numan, Nels, Qian, Xun, Chen, Yanhe, Zhou, Zhongyi, Chen, Xingyue, Ren, Jiahao, Bettridge, Robert Timothy, Chen, Xiang 'Anthony', Faruqi, Faraz, Toh, Steve, Kim, David
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913002067853312
author Du, Ruofei
Hersh, Benjamin
Li, David
Numan, Nels
Qian, Xun
Chen, Yanhe
Zhou, Zhongyi
Chen, Xingyue
Ren, Jiahao
Bettridge, Robert Timothy
Chen, Xiang 'Anthony'
Faruqi, Faraz
Toh, Steve
Kim, David
author_facet Du, Ruofei
Hersh, Benjamin
Li, David
Numan, Nels
Qian, Xun
Chen, Yanhe
Zhou, Zhongyi
Chen, Xingyue
Ren, Jiahao
Bettridge, Robert Timothy
Chen, Xiang 'Anthony'
Faruqi, Faraz
Toh, Steve
Kim, David
contents While large language models (LLMs) have accelerated 2D software development through intent-driven "vibe coding", prototyping intelligent Extended Reality (XR) experiences remains a major challenge. The fundamental barrier is not just the steep learning curve for human creators, but that low-level sensor APIs and complex game engine hierarchies are ill-suited for LLM reasoning, routinely exceeding context windows and inducing syntax hallucinations. To bridge this gap, we contribute XR Blocks, an open-source, LLM-native WebXR framework. Unlike traditional engines, XR Blocks introduces a semantic "Reality Model" that aligns spatial computing primitives (users, physical environments, and agents) with natural language, providing a robust, concise vocabulary optimized for generative AI. Building upon this foundation, we present Vibe Coding XR, an end-to-end prototyping workflow that leverages LLMs to translate high-level prompts (e.g., "create a dandelion that reacts to my hand") directly into functional, physics-aware mixed-reality applications. To minimize the friction of on-device testing, the workflow introduces a seamless desktop "simulated reality" to headset deployment loop. Finally, we introduce VCXR60, a pilot dataset of 60 XR prompts paired with an automated evaluation pipeline. Our technical evaluation demonstrates high one-shot execution success, enabling practitioners to bypass lowlevel hurdles and rapidly move from "idea to reality". Code and live demos are available at https://github.com/google/xrblocks and http://xrblocks.github.io/gem.
format Preprint
id arxiv_https___arxiv_org_abs_2603_24591
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Vibe Coding XR: Accelerating AI + XR Prototyping with XR Blocks and Gemini
Du, Ruofei
Hersh, Benjamin
Li, David
Numan, Nels
Qian, Xun
Chen, Yanhe
Zhou, Zhongyi
Chen, Xingyue
Ren, Jiahao
Bettridge, Robert Timothy
Chen, Xiang 'Anthony'
Faruqi, Faraz
Toh, Steve
Kim, David
Human-Computer Interaction
While large language models (LLMs) have accelerated 2D software development through intent-driven "vibe coding", prototyping intelligent Extended Reality (XR) experiences remains a major challenge. The fundamental barrier is not just the steep learning curve for human creators, but that low-level sensor APIs and complex game engine hierarchies are ill-suited for LLM reasoning, routinely exceeding context windows and inducing syntax hallucinations. To bridge this gap, we contribute XR Blocks, an open-source, LLM-native WebXR framework. Unlike traditional engines, XR Blocks introduces a semantic "Reality Model" that aligns spatial computing primitives (users, physical environments, and agents) with natural language, providing a robust, concise vocabulary optimized for generative AI. Building upon this foundation, we present Vibe Coding XR, an end-to-end prototyping workflow that leverages LLMs to translate high-level prompts (e.g., "create a dandelion that reacts to my hand") directly into functional, physics-aware mixed-reality applications. To minimize the friction of on-device testing, the workflow introduces a seamless desktop "simulated reality" to headset deployment loop. Finally, we introduce VCXR60, a pilot dataset of 60 XR prompts paired with an automated evaluation pipeline. Our technical evaluation demonstrates high one-shot execution success, enabling practitioners to bypass lowlevel hurdles and rapidly move from "idea to reality". Code and live demos are available at https://github.com/google/xrblocks and http://xrblocks.github.io/gem.
title Vibe Coding XR: Accelerating AI + XR Prototyping with XR Blocks and Gemini
topic Human-Computer Interaction
url https://arxiv.org/abs/2603.24591