GenXR-Bench：首个XR软件开发中编码智能体评估基准发布
【US】XR coding 是另一套长程：UCLA/Google GenXR（ICLR 2027），最强仅 50.9% Pass@1
反直觉：XR 应用要在连续用户运动、空间输入与环境传感下运行时稳健，不是普通仓库级 coding。现有错处：用通用 SWE 分外推 XR。作者改动：GenXR-Bench——**112** 专家任务（24 功能/21 修 bug/67 应用生成）。硬数字：测试套相对盲测专家判断准确率 **96.5%**；最强配置整体 Pass@1 仅 **50.9%**。可迁移判断：**明川：XR/交互 3D agent 必须用运行时断言评测，禁只测静态编译。不要并进 #18 RegretBench，也不要并进昨版 WildAWM。**
GenXR-Bench (arXiv:2610.29014)
“Authors: William Huang , David Li , Xiang 'Anthony' Chen , Xun Qian , Nels Numan , Zhongyi Zhou , Hyunsung Cho , Salman Muin Kayser Chishti”
Authors:William Huang, David Li, Xiang 'Anthony' Chen, Xun Qian, Nels Numan, Zhongyi Zhou, Hyunsung Cho, Salman Muin Kayser Chishti, Ding Xia, Xincheng Huang, Jiahao Ren, Faraz Faruqi, Tianyu Xu, Yang Zhang, David Kim, Ruofei Du
Abstract:Coding agents are rapidly advancing from single-file generation to long-horizon repository-scale engineering, yet the evaluation of their capabilities to author interactive extended reality (XR) applications remains an open challenge. Unlike traditional software, XR applications operate within dynamic 3D physical environments where runtime robustness depends jointly on continuous user motion, spatial input, and environmental sensing. We introduce GenXR-Bench, the first benchmark for the end-to-end evaluation of coding agents in XR software development. GenXR-Bench contains 112 expert-authored tasks spanning 24 feature implementations, 21 bug repairs, and 67 application generation tasks. Held-out tests combine scripted and adaptive interactions with programmatic and visual assertions to evaluate core functionality and runtime behavior. GenXR-Bench's testing suite achieves 96.5% accuracy against blinded expert judgments of 124 candidate applications executed on consumer XR hardware. Evaluating 10 models on GenXR-Bench, we find that the strongest configuration achieves only 50.9% overall Pass@1. Failure analysis identifies recurring misunderstandings in asynchronous sensor lifecycles, physical grounding, and embodied interaction semantics. GenXR-Bench establishes a reproducible testbed for evaluating coding agents in the interactive and physically situated conditions of spatial computing.
| Comments: | 37 pages, 10 figures. Code available at this https URL |
| Subjects: | Artificial Intelligence (cs.AI); Graphics (cs.GR); Human-Computer Interaction (cs.HC) |
| Cite as: | arXiv:2610.29014 [cs.AI] |
| (or arXiv:2610.29014v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.29014 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: William Huang [view email]
[v1]
Wed, 21 Oct 2026 00:28:16 UTC (30,978 KB)
来源：Agent Control Flash News · arxiv.org
关联产品与深度拆解
Cursor Agent 架构全景拆解：从影子工作区到多文件推演引擎
全面剖析 Cursor 在 Agent 模式下的底层技术实现，解析影子分支隔离、LSP 上下文剪枝以及预测性补全的核心架构细节与工程实践经验。
Vercel v0 推出全新多 Agent 协作画布与实时全栈部署预览
动态速评：v0 正在从单一组件生成器演进为全栈应用搭建协作台，尤其是与 Neon/Postgres 的直连极大降低了全栈原型验证成本。