发表机构
Google（谷歌）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出一种将设计方向作为显式中间决策的推理架构，通过结构化设计规范采样实现氛围设计代理的创造性探索，在保持生成设置固定的同时拓宽UI备选方案，并验证其可行性与成本效益。
AI 中文摘要
氛围设计代理将自然语言简报转化为渲染界面和前端代码。然而，一个有用的设计代理应不止于生成一个有效页面：它应帮助用户探索连贯的备选方案。提高token级温度是一种生硬的解决方案，因为它同时改变美学决策和语法敏感的代码。我们转而通过一种推理架构将探索与实现分离，该架构使设计方向成为显式的中间决策。受口头化采样的启发，一个预通过步骤提出带有典型性评分的结构化设计规范，一个外部选择器对其中一个进行采样，下游生成器在固定设置下结合原始请求实现所选规范。我们将此方法应用于UI主题和视觉资产提示。在168个提示中，每个干预措施在每个温度下进行1,255次配对比较，主题采样拓宽了观察到的选择覆盖范围和截图变化，而LLM评判者的偏好因干预措施、提示复杂性和视口而异。在一项超过300,000个任务的在线实验中，观察到的代码导出增加在统计上仍不确定，而更少的负面反馈事件与更多的纠正交互和适度的操作成本并存。综合来看，这些发现将结构化设计规范确定为在保持下游生成设置固定的同时探索备选UI概念的实际控制点。
英文摘要
Vibe design agents turn natural-language briefs into rendered interfaces and frontend code. Yet a useful design agent should do more than produce one valid page: it should help users explore coherent alternatives. Increasing token-level temperature is a blunt solution because it varies aesthetic decisions and syntax-sensitive code at the same time. We instead separate exploration from implementation through an inference architecture that makes design direction an explicit intermediate decision. Inspired by Verbalized Sampling, a pre-pass proposes structured design specifications with typicality scores, an external selector samples one, and the downstream generator realizes the selected specification together with the original request under fixed settings. We apply this approach to UI themes and visual-asset prompts. Across 168 prompts, with 1,255 paired comparisons per temperature for each intervention, theme sampling broadens observed selection coverage and screenshot variation, while LLM-judge preferences vary across interventions, prompt complexity, and viewport. In an online experiment with more than 300,000 tasks, the observed code-export increase remains statistically uncertain, while fewer negative feedback events coexist with more correction interactions and modest operational costs. Together, these findings identify structured design specifications as a practical control point for exploring alternative UI concepts while keeping downstream generation settings fixed.
Comments14 pages, 3 figures
