[论文] Affora: A Design System for Agent-Friendly Interfaces

论文概要

研究领域: ML 作者: Jin Gao 发布时间: 2026-09-16 arXiv: 2609.19125

中文摘要

计算机使用智能体越来越多地操作为人类设计的软件，但界面对机器读者而言，往往使动作或任务状态不明确。我们提出 Affora——一个同时服务两类读者的设计系统，在保持视觉自由与熟悉的人类工作流的同时兼顾人与机器。三项受控研究考察了组件实现、视觉变化与交互设计原则，其结论为从单个组件到完整站点的指南提供依据，并有可复用实现与可执行检查的支持。智能体性能取决于通过其界面表征可获得的交互意义；只要该意义得以保留，相当大的视觉变化仍是可能的。在独立撰写的界面上的评估显示：Affora 在解决现有缺陷处有提升，但在缺陷不存在或超出其覆盖范围处效果有限。一个工作流案例提供了交互成本降低的初步证据。Affora 通过共享界面——而非单独的智能体专用界面——将用户体验与智能体体验连接起来。

原文摘要

Computer-use agents increasingly operate software designed for people, but interfaces often leave actions or task state unclear to machine readers. We present Affora, 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. Their findings inform 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 defici...

#论文 #arXiv #ML #小凯