arXiv：cs.AI· Jinliang Xu·· 5 小时前
OpenAgenet / OAN 黄皮书：面向可信治理资源身份与发现的技术架构
OpenAgenet / OAN Yellow Paper: Technical Architecture for Trust-Governed Resource Identity and Discovery
AI 导读
OpenAgenet / OAN 黄皮书发布，描述了一套协议中立的信任层架构，用于开放 Agent 互联与可发现的 AI 资源产品。该架构定义了 did:oan 身份对象、注册流程、基于治理的 Root 生命周期、授权感知发现与签名可信调用等机制。OAN 支持 MCP、A2A、ANP 类系统、Skills、MCP Servers 及 Tool/API 资源等异构 Agent 框架与交互协议。
正文
Abstract:This yellow paper describes the technical architecture of OpenAgenet / OAN. OAN is a protocol-neutral trust layer for open Agent interconnection and discoverable AI resource products. It specifies the role architecture, \texttt{did:oan} identity objects, registration workflow, governance-backed Root lifecycle enforcement, Root-verified package model, authorization-aware Discovery, Root-issued infrastructure authorization VCs, signed trusted invocation, verification requirements, state transitions, security properties, implementation boundaries, and deployment considerations. The design is intended to support heterogeneous Agent frameworks and interaction protocols, including MCP, A2A, ANP-like systems, domain-specific Agent protocols, Skills, MCP Servers, and Tool/API resources. OAN does not define the entire business conversation among Agents or the native protocol of every resource; it defines how resource identities become admissible, discoverable, verifiable, and safe to approach before protocol-specific interaction begins.
| Subjects: | Multiagent Systems (cs.MA); Artificial Intelligence (cs.AI); Distributed, Parallel, and Cluster Computing (cs.DC) |
| Cite as: | arXiv:2606.03163 [cs.MA] |
| (or arXiv:2606.03163v5 [cs.MA] for this version) | |
| https://doi.org/10.48550/arXiv.2606.03163 arXiv-issued DOI via DataCite |
Submission history
From: Jinliang Xu [view email]
[v1]
Tue, 2 Jun 2026 05:18:14 UTC (144 KB)
[v2]
Wed, 3 Jun 2026 04:53:20 UTC (144 KB)
[v3]
Fri, 5 Jun 2026 05:42:43 UTC (149 KB)
[v4]
Mon, 31 Aug 2026 12:53:00 UTC (374 KB)
[v5]
Mon, 12 Oct 2026 05:26:39 UTC (377 KB)
来源：arXiv：cs.AI · arxiv.org