PulseAugur
中
实时 12:03:09
English(EN) WebUIProof: Benchmarking WebUI Code Generators with UI-Agent Execution Harness

新的 WebUIProof 基准测试揭示了 LLM 生成代码中的功能缺陷

研究人员推出了 WebUIProof,这是一个旨在严格评估 WebUI 代码生成功能正确性的新基准。该基准利用 UI-agent 执行工具,在无头浏览器中模拟用户交互,以根据指定的断言测试生成的代码。对八个商业 LLM 的评估显示,基于交互的需求经常失败,尤其是在复杂的 3D 模拟界面方面。研究还表明,使用从这些交互测试中获得的强化学习信号来训练 Qwen2.5 14B 和 MIMO 7B 等较小模型,可以提高功能完成率并减少构建错误。 AI

影响 突出了 LLM 在交互式界面代码生成方面的关键差距,并提出了改进功能正确性的新训练方法。

排序理由 介绍新基准和评估方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

新的 WebUIProof 基准测试揭示了 LLM 生成代码中的功能缺陷

本文如何被排名

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
介绍新基准和评估方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
2 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
Topics
paper, product
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
3 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.
Coverage growth since scoring
+1 source(s) since last score
New sources have picked up this story since our last re-score. Score will update on the next scoring pass.

完整方法见我们的编辑标准。

报道来源 [2]

  1. arXiv cs.AI TIER_1 English(EN) · Yun-Yun Tsai, Yuning Mao, Shiqi Wang, Junfeng Yang, Sinong Wang ·

    WebUIProof:使用 UI-Agent 执行框架对 WebUI 代码生成器进行基准测试

    arXiv:2610.02617v1 Announce Type: cross 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)…

  2. arXiv cs.MA (Multiagent) TIER_1 English(EN) · Sinong Wang ·

    WebUIProof:使用 UI-Agent 执行框架对 WebUI 代码生成器进行基准测试

    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 We…