LLMs can now produce full HTML pages, but many of those pages are only superficially correct: they render once, then fail under scroll, hover, click, resize, or gameplay. Evaluation from screenshots can miss these failures, and filtering discards many pages that are still repairable. We introduce HTMLCure, a browser experience framework that evaluates HTML after the system has interacted with it. The evaluator executes the page across viewports and interaction states, records deterministic browser evidence, and gives the VLM curated keyframes from the executed trajectory rather than isolated screenshots. The same state signal drives a closed loop repair engine: HTMLCure diagnoses the current page, chooses a state specific repair family, runs each candidate again, and exports quality cleared pages for SFT. On a 97K prompt corpus, this expands the directly usable seed into a candidate pool of 63703 quality cleared pages, from which we construct the final refined SFT set of 40K pages. Under the same backbone and training recipe, HTMLCure-27B-Refined reaches 50.6 on HTMLBench-400 with 45.2% deterministic test case pass, placing it in the same performance band as strong reference rows such as Kimi-K2.6 and GPT-5.4. On the released MiniAppBench validation split, it reaches 81.2 average, improving raw 27B SFT by 15.3 points and approaching the level of strong reference systems.

翻译：大语言模型如今能够生成完整的HTML页面，但许多页面仅表面正确：它们能渲染一次，却在滚动、悬停、点击、缩放或游戏场景中失效。基于截图的评估可能遗漏这些故障，而过滤机制又会丢弃大量仍可修复的页面。我们提出HTMLCure——一种浏览器体验框架，它在系统与HTML交互后对其进行评估。评估器跨视口和交互状态执行页面，记录确定性的浏览器证据，并向视觉语言模型提供从执行轨迹中提取的精选关键帧，而非孤立的截图。相同的状态信号驱动闭环修复引擎：HTMLCure诊断当前页面，选择特定于状态的修复族，再次运行每个候选方案，并导出质量清洁的页面用于监督微调。在97K提示语料库上，该方法将可直接使用的种子扩展为63,703个质量清洁页面的候选池，并从中构建最终精炼的40K页面监督微调数据集。在相同骨干网络和训练策略下，HTMLCure-27B-Refined在HTMLBench-400上达到50.6分，确定性子测试用例通过率为45.2%，与Kimi-K2.6和GPT-5.4等强基线模型处于同一性能区间。在发布的MiniAppBench验证集上，其平均分达到81.2分，较原始27B监督微调模型提升15.3分，接近强参考系统的水平。