AUV-Bench: Aesthetic Understanding and Generation Evaluation for User Interfaces
作者: Zhijie Deng, Ling Li, Junhao Ji, Siwei Lyu, Zhipeng Xu, Zulong Chen, Rongyao Fang, Shuai Bai, Xuming Hu, Jiaheng Wei
分类: cs.AI
发布日期: 2026-09-28
💡 一句话要点
提出AUV-Bench以解决用户界面美学评估与生成问题
🎯 匹配领域: 支柱九：具身大模型 (Embodied Foundation Models)
关键词: 用户界面设计 美学评估 多模态模型 设计原则 智能生成
📋 核心要点
- 现有多模态模型在用户界面美学评估中表现出与人类设计师的显著差异，缺乏系统的美学理解。
- AUV-Bench通过与专业UI设计师合作，构建了一个包含1395个网页界面的评估框架，涵盖美学评分、诊断、修复和生成任务。
- 实验结果表明，模型在美学评分上与设计师有中等一致性，但在诊断和修复任务中表现不佳，揭示了判断与行动之间的差距。
📝 摘要（中文）
多模态基础模型在用户界面（UI）评估和生成中越来越多地被使用，尽管它们能够产生看似合理的美学判断和视觉上可信的页面，但在专业设计审查下，其行为与人类设计师有显著差异。设计师依赖一套系统的美学原则来指导判断、诊断、修复和创作。现有评估通常孤立地评估这些能力，难以确定任务级成功是否反映共享的美学理解。为了解决这一问题，本文提出了AUV-Bench，基于1395个可执行的网页界面和四个任务（美学评分、诊断、修复和文本到UI生成）进行开发。评估结果显示，模型在整体美学评分上与专业设计师有中等一致性，但在诊断链成功率上仅达到24.7%。
🔬 方法详解
问题定义：论文旨在解决现有多模态模型在用户界面美学评估与生成中的不足，尤其是缺乏系统的美学理解和设计行动的连贯性。现有方法往往孤立评估能力，难以反映真实的设计过程。
核心思路：AUV-Bench的核心思路是通过构建一个包含多种任务和美学原则的评估框架，连接美学判断与设计行动，以实现更全面的能力评估。
技术框架：该框架包括四个主要任务：美学评分、诊断、修复和文本到UI生成，所有任务共享一组UI和美学原则，并在660个控制降级实例上进行对齐分析。
关键创新：AUV-Bench的创新之处在于其系统性地将美学判断与设计行动结合起来，填补了现有评估方法中的空白，特别是在诊断和修复任务中的实例级分析。
关键设计：在实验中，模型的评估使用了特定的损失函数和参数设置，以确保在美学评分和诊断链的准确性上进行优化。
🖼️ 关键图片
📊 实验亮点
实验结果显示，模型在整体美学评分上与专业设计师的中等一致性为72.3%，但在诊断链成功率上仅达到24.7%。在开放式生成任务中，领先模型的美学质量仅为中等水平，表明当前模型在美学理解和判断行动的连贯性上仍有待提升。
🎯 应用场景
AUV-Bench的研究成果可广泛应用于用户界面设计领域，帮助设计师和开发者更好地理解和生成美学优良的界面。通过提供系统的评估框架，该工具能够提高设计过程的效率和质量，未来可能推动智能设计助手的发展。
📄 摘要（原文）
Multimodal foundation models are increasingly used for evaluating and generating user interfaces (UIs), often producing seemingly reasonable aesthetic judgments and visually plausible pages. However, under professional design scrutiny, their behavior can differ substantially from that of human designers. In professional design practice, designers rely on a systematic set of aesthetic principles that consistently guide judgment, diagnosis, repair, and creation. A coherent aesthetic capability should therefore connect aesthetic judgment with design actions. Existing evaluations, however, typically assess these abilities in isolation, making it difficult to determine whether task-level success reflects a shared aesthetic understanding or merely fragmented task-specific competence. To address this gap, we introduce AUV-Bench, developed in collaboration with professional UI designers around 1,395 executable web interfaces and four tasks: aesthetic scoring, diagnosis, repair, and text-to-UI generation. The tasks share a pool of UIs and aesthetic principles, with diagnosis and repair further aligned on 660 controlled-degradation instances to enable instance-level analysis of judgment and action. Evaluation of 12 models reveals a capability imbalance: models show moderate agreement with professional designers in holistic aesthetic scoring, yet exact diagnosis-chain success peaks at only 24.7%. On the aligned diagnosis-repair cases, correct judgments and successful repairs do not consistently coincide, exposing a Judgment-Action Gap between identifying aesthetic problems and successfully acting on them. In open-ended generation, even leading models achieve only moderate aesthetic quality under human-calibrated evaluation. Overall, current models exhibit partial aesthetic competence, but still lack the fine-grained understanding and judgment-action coherence required for reliable UI design.