Source: Affora: A Design System for Agent-Friendly Interfaces · platform: arxiv · authors: Jin Gao · date: 2026-09-16
TL;DR（中文摘要）
Computer-use agent 越来越多地操作“为人设计”的软件，但现有界面常把操作含义或任务状态对机器读者隐藏。Affora 提出一个同时服务两类读者的设计系统：在保留人类视觉自由度与熟悉工作流的前提下，让 agent 也能从界面表示中读出交互含义。三项受控研究分别覆盖组件实现、视觉变化与交互设计原则，产出从单个组件到完整站点的指导，并附可复用实现与可执行检查。核心结论：agent 性能取决于界面表示中可用的交互含义；只要含义保住，视觉上仍有很大变化空间。在独立作者编写的界面上评测，Affora 在存在缺陷处带来提升，在缺陷不存在或超出覆盖范围处效果有限。一个工作流案例初步显示交互成本下降。Affora 通过共享界面把 UX 与 agent experience 连接起来，而不是另建 agent 专用表面。
Summary (English)
Computer-use agents increasingly operate software designed for people, but interfaces often leave actions or task state unclear to machine readers. Affora is a design system that supports both readers while preserving visual freedom and familiar human workflows. Three controlled studies examine component implementations, visual variation, and interaction-design principles, informing guidance from individual components to complete sites, supported by reusable implementations and executable checks. Agent performance depends on the interaction meaning available through its interface representation; substantial visual variation remains possible when that meaning is preserved. Evaluation on independently authored interfaces shows gains where Affora addresses existing deficits, but limited effects where those deficits are absent or outside its coverage. A workflow case provides preliminary evidence of reduced interaction cost. Affora connects user experience and agent experience through a shared interface rather than a separate agent-only surface.
入库依据
opencli arxiv paper 2609.19125 -f json 抓取 arXiv 元数据（标题/作者/摘要/分类/日期），内容由摘要直接支撑。
补充
arXiv 2609.19125，primary cs.HC，categories: cs.HC, cs.AI, cs.SE；comment: 20 pages, 8 figures；submitted 2026-09-16。