以评分标准作为视觉修复上下文的自演化UI到代码生成

摘要

大型视觉语言模型在UI到代码生成方面展现出显著进展，但其测试时自我进化仍不稳定。我们首先识别出一个根本性障碍，称为视觉修复耦合：局部的代码编辑可能通过布局、样式和组件依赖关系进行传播，在修正一处视觉不匹配的同时，使先前保真度良好的区域发生退化。为解决这一问题，我们提出RubSE——一种基于评分标准的自我进化框架，利用评分标准将视觉反馈表示为结构化的视觉修复上下文。在每轮优化中，RubSE生成类型化候选评分标准，选择一个优先修复目标，并将先前选定的评分标准存储为历史记录，从而引导每次修订朝向范围明确的视觉修复，同时抑制重复或过度宽泛的更改。在六个视觉语言模型和三个UI到代码基准上的评估表明，RubSE在最终轮和最佳轮设置中均显著优于朴素自我进化，实现了更稳定的优化轨迹和更高的轨迹级性能上限。进一步分析表明，RubSE通过改善严重视觉回退后的恢复能力来缓解轨迹坍缩，且更强的评分标准生成器能够将有效的视觉修复指导迁移至较弱的代码改进器。

English

Large vision-language models have shown strong progress in UI-to-code generation, yet their test-time self-evolution remains unstable. We first identify a fundamental obstacle, termed visual repair coupling: a local code edit may propagate through layout, style, and component dependencies, correcting one visual mismatch while degrading regions that were previously faithful. To address this issue, we present RubSE, a Rubric-guided Self-Evolution framework that uses rubrics to represent visual feedback as a structured visual-repair context. At each refinement round, RubSE generates typed candidate rubrics, selects one prioritized repair target, and stores previously selected rubrics as history, thereby steering each revision toward a well-scoped visual repair while discouraging repeated or over-broad changes. Evaluations across six VLMs and three UI-to-code benchmarks demonstrate that RubSE substantially outperforms naïve self-evolution in final-round and best-round settings, achieving more stable refinement trajectories and a higher trajectory-level performance ceiling. Further analysis shows that RubSE mitigates trajectory collapse by improving recovery from severe visual regressions, and that stronger rubric generators can transfer effective visual-repair guidance to weaker code improvers.