arXiv：cs.AI· Yun-Yun Tsai, Yuning Mao, Shiqi Wang, Junfeng Yang, Sinong Wang·· 4 小时前AI 评分44
WebUIProof：用 UI-Agent 执行测试框架评测 WebUI 代码生成器
WebUIProof: Benchmarking WebUI Code Generators with UI-Agent Execution Harness
AI 导读
WebUIProof 是一个面向 WebUI 代码生成的执行型基准，提供结构化规格与可执行交互测试，覆盖通用 WebUI 和 3D 交互仿真两类任务。其 UI-agent 测试框架在无头浏览器中以 plan-act-observe 循环定位 DOM、执行操作并校验断言，对八款商业 LLM 的评测显示，页面渲染成功仍常在交互需求上失败，3D 仿真界面尤为明显。
正文
Abstract:Evaluating WebUI code generation at scale is difficult: outputs may compile and look plausible yet fail under user interaction, and prior benchmarks largely rely on free-form prompts with static checks (build success, screenshots) that miss functional correctness. We introduce WebUIProof, an execution-oriented benchmark that provides structured specifications and dense, executable interaction tests for WebUI generation across two task families: general WebUIs (e.g., dashboards, game, interactive tools) and 3D interactive simulation (e.g., particle/galaxy systems, physics dynamics). WebUIProof includes a UI-agent harness that runs executable interaction tests in a headless browser using an iterative plan--act--observe loop: it locates DOM elements, performs actions, observes resulting UI/DOM changes, and checks the specified assertions. We evaluate across eight commercial LLMs and observe frequent failures on interaction-based requirements even when pages render successfully, especially on 3D simulation interfaces. Finally, we show the UI-agent harness can provide outcome-level training signals. Training compact models (e.g., Qwen2.5 14B and MIMO 7B) with RL rewards derived from executable interaction tests improves functional completion while reducing build failures.
| Comments: | 43 pages |
| Subjects: | Software Engineering (cs.SE); Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA) |
| Cite as: | arXiv:2610.02617 [cs.SE] |
| (or arXiv:2610.02617v1 [cs.SE] for this version) | |
| https://doi.org/10.48550/arXiv.2610.02617 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yun-Yun Tsai [view email]
[v1]
Fri, 2 Oct 2026 00:17:11 UTC (30,287 KB)
来源：arXiv：cs.AI · arxiv.org