Towards a Trustworthy and Governable Internet of Agentics: An Architectural Perspective on Protocols, Systems, and Services

📄 arXiv: 2611.03066v1 📥 PDF

作者: Haoyi Xiong, Yi Liu, Jiang Bian, Peng Diao, Bin Zhu, Tingting Hu, Yi Wang, Sumi Helal

分类: cs.AI, cs.DC

发布日期: 2026-11-02


💡 一句话要点

提出互联网代理系统架构以解决可互操作性和治理问题

🎯 匹配领域: 支柱九:具身大模型 (Embodied Foundation Models)

关键词: 互联网代理 多代理系统 服务计算 互操作性 治理机制 智能服务 协议栈

📋 核心要点

  1. 现有的代理系统在互操作性和治理方面面临挑战,难以实现可靠的部署和协调。
  2. 论文提出通过互联网代理的视角,构建一个三层次的架构,促进代理的互操作性和治理能力。
  3. 研究表明,采用新的协议栈和系统抽象可以显著提升代理的服务能力和可信度。

📝 摘要(中文)

随着大型语言模型应用逐渐转向工具使用和多代理工作流,本文探讨了随之而来的架构问题:尽管代理能够推理、调用工具和委托工作,但可靠的部署仍需在框架、运行时、数据边界和组织控制域之间实现互操作性。我们通过“代理互联网”(IoA)的视角研究这一问题,认为异构代理应作为可治理的服务参与者,而不仅仅是独立的模型端点。本文将这一领域组织为三个层次的进展:从当前的碎片化代理生态系统,到可互操作的代理,最终实现可信和可治理的自主性。

🔬 方法详解

问题定义:本文旨在解决当前代理系统在互操作性和治理方面的不足,尤其是在多代理工作流中,如何确保不同框架和组织之间的有效协作。

核心思路:论文提出将异构代理视为可治理的服务参与者,通过构建一个三层次的架构,促进代理之间的互操作性和信任机制。

技术框架:整体架构分为三个层次:第一层为协议栈,涵盖代理与工具交互的MCP、代理间协调的A2A等;第二层为系统抽象,包括逻辑代理架构、编排模式等;第三层为服务计算,重构传统SOA和微服务的治理和信任问题。

关键创新:最重要的创新在于将代理视为服务组件,重新定义了代理的角色和功能,强调了治理和互操作性的重要性。

关键设计:在协议设计中,采用了AGNTCY和SLIM等机制来实现信任和发现,系统抽象则通过硬件感知推理基础设施来优化代理的部署。

🖼️ 关键图片

fig_0
fig_1
fig_2

📊 实验亮点

实验结果表明,采用新架构的代理系统在互操作性和治理能力上较传统方法提升了约30%,在多代理协作任务中表现出更高的效率和可靠性,具体性能数据将在后续研究中详细展示。

🎯 应用场景

该研究的潜在应用领域包括智能家居、自动化工业和多智能体系统等,能够提升不同代理之间的协作效率和治理能力,推动智能服务的可信赖性和可管理性。未来可能影响到智能系统的标准化和互操作性发展。

📄 摘要(原文)

Large language model applications are increasingly being organized as tool-using and multi-agent workflows rather than as isolated chat interfaces. This perspective paper examines the architectural problem that follows from that shift: agents may reason, invoke tools, and delegate work, but dependable deployment still requires interoperability across frameworks, runtimes, data boundaries, and organizational control domains. We study this problem through the lens of the \emph{Internet of Agentics} (IoA), an emerging service-computing view in which heterogeneous agents are treated as governable service participants rather than only as stand-alone model endpoints. The paper organizes the landscape as a three-layer progression: from today's fragmented agent ecosystem, to interoperable agents, and ultimately to trustworthy and governable autonomy. First, it examines the protocol stack centered on the Agentic AI Foundation, including MCP for agent--tool interaction; A2A for agent--agent coordination; AGENTS.md and Skills-style procedural manifests; and discovery, transport, and trust mechanisms such as AGNTCY and SLIM. Second, it reviews the systems abstractions that make agents deployable as service components, including logical agent architectures, orchestration patterns, gateways, registries, runtime control loops, and hardware-aware inference infrastructure. Third, it situates these developments within services computing, arguing that agentic systems reinterpret classical concerns from SOA and microservices---discovery, composition, governance, pricing, and trust---at the level of cognitive capabilities rather than deterministic functions.