arXiv cs.AI· Dario Fenoglio, Martin Gjoreski, Marc Langheinrich, Pradyumna Chari, Ramesh Raskar·· 4 小时前AI 评分42
WebAgents:将智能体创建、托管与执行解耦的智能体原生 Web
WebAgents: Unbundling Agent Creation, Hosting, and Execution for an Agent-Native Web
AI 导读
WebAgents 通过签名包将智能体的创建、托管与执行解耦,包内携带可移植的工作流、技能、schema 和资源需求。基于 OpenClaw 的智能体原生浏览器/运行时负责验证包、获取授权,并在运行时绑定用户控制的模型、工具、权限与预算。
正文 · 原文
Abstract:Large language models are moving from isolated assistants toward autonomous agents that can plan, use tools, and coordinate with others, motivating an emerging Agentic Web of independently developed agents and services. Realizing this vision requires agent behavior to move across creators, hosts, and runtimes without coupling publication to a particular execution environment or transferring authority over user resources. We introduce WebAgents, which unbundles these roles through a signed this http URL that carries portable workflows, skills, schemas, and resource requirements. An OpenClaw-based agent-native browser/runtime verifies the package, obtains authorization, and binds it at run time to user-controlled models, tools, permissions, and budgets, while hosts distribute the public program and may retain private services server-side. We demonstrate this contract with three unrelated workflows executed unchanged under local and API-backed models, including literature review with live services and a website-published travel agent using semantic tools and user-selected personal resources. In a controlled suite, WebAgents explicitly blocks all 716 injected contract violations while accepting all 295 matched benign controls, with median automated pre-execution processing below 0.5 s for all three packages. We conclude by outlining a path toward NANDA-based discovery and interoperable package ecosystems while retaining execution authority in the user's runtime.
| Comments: | Presented at IEEE CIC 2026. 8 pages |
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.21978 [cs.AI] |
| (or arXiv:2611.21978v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.21978 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Dario Fenoglio [view email]
[v1]
Mon, 16 Nov 2026 23:05:11 UTC (90 KB)
来源:arXiv cs.AI · arxiv.org