构建面向智能体的网络：一种声明式智能体-网络交互框架

摘要

网络上自主AI代理的日益部署正面临一个根本性错位障碍：代理必须从面向人类的用户界面推断功能可见性，导致交互变得脆弱、低效且不安全。为此，我们推出VOIX——一种原生网络框架，通过简单的声明式HTML元素，使网站能够为AI代理提供可靠、可审计且保护隐私的能力。VOIX引入<tool>和<context>标签，允许开发者明确定义可用操作与相关状态，从而建立清晰的机器可读行为契约。该方法将控制权转移至网站开发者，同时通过将会话交互与网站分离来保护用户隐私。我们通过为期三天的黑客马拉松研究（16名开发者参与）评估了该框架的实用性、易学性和表达力。结果表明，无论参与者先前经验如何，都能快速构建多样化且功能完善的代理驱动型网络应用。这项研究最终为实现"代理化网络"提供了基础机制，为未来网络中人机无缝安全协作开辟了道路。

English

The increasing deployment of autonomous AI agents on the web is hampered by a fundamental misalignment: agents must infer affordances from human-oriented user interfaces, leading to brittle, inefficient, and insecure interactions. To address this, we introduce VOIX, a web-native framework that enables websites to expose reliable, auditable, and privacy-preserving capabilities for AI agents through simple, declarative HTML elements. VOIX introduces <tool> and <context> tags, allowing developers to explicitly define available actions and relevant state, thereby creating a clear, machine-readable contract for agent behavior. This approach shifts control to the website developer while preserving user privacy by disconnecting the conversational interactions from the website. We evaluated the framework's practicality, learnability, and expressiveness in a three-day hackathon study with 16 developers. The results demonstrate that participants, regardless of prior experience, were able to rapidly build diverse and functional agent-enabled web applications. Ultimately, this work provides a foundational mechanism for realizing the Agentic Web, enabling a future of seamless and secure human-AI collaboration on the web.

构建面向智能体的网络：一种声明式智能体-网络交互框架

Building the Web for Agents: A Declarative Framework for Agent-Web Interaction

摘要

Support