arXiv cs.AI· Yuqi Qiu, Zuyao Xu, Lu Sun, Xiang Li, Fasheng Miao, Fubin Wu, Haixin Duan, Zheli Liu·· 2 小时前AI 评分39
Agent Transfer Protocol（ATP）：面向 Agentic Web 的服务器中介式 Agent 间通信架构
Agent Transfer Protocol: Server-Mediated Agent-to-Agent Communication Architecture for the Agentic Web
AI 导读
研究者提出跨组织 Agent 通信协议 ATP（Agent Transfer Protocol），采用域中介架构：管理域为逻辑 Agent 维护稳定地址和接收入口，双方域服务器持续承担跨域传输，发送域对完整消息信封签名。接收域代为验证并保存消息，使执行实例可在离线或被替换后独立复核域来源与内容完整性。团队实现了原型，并通过跨组织 LLM Agent 工作流、机制检查和延迟测量完成了评估。
正文 · 原文
Abstract:The Agentic Web needs to support continuous collaboration among agents from different organizations. These collaborative relationships may span multiple tasks, network connections and execution instances. Such interactions require stable communication entries, message reception when instances are offline, and source verification after delayed reading. How to organize these responsibilities so that cross domain communication does not depend on specific execution instances being continuously online is a key issue for building long term agent interaction infrastructure. We propose ATP (Agent Transfer Protocol), a cross organization agent communication protocol adopting a domain mediated architecture. In this architecture, administrative domains maintain stable addresses and receiving entries for logical agents. The domain servers of both parties continuously undertake cross domain transmission. The receiving domain verifies and saves messages for execution instances to read later. The sending domain signs the complete message envelope. This allows the receiving instance to independently reverify the domain source and content integrity after the original connection ends, provided the original verification public key is still trusted and obtainable. We implemented an ATP prototype and evaluated it through a controlled cross organization LLM agent workflow, mechanism checks and latency measurements. The workflow completed subsequent business processing after instances went offline or were replaced. The independent verifier successfully verified the domain source and content integrity of saved messages. Latency measurements further quantified the communication and processing overhead introduced by the continuous mediation of domain servers.
| Comments: | 12 pages, 6 figures, 5 tables |
| Subjects: | Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA) |
| Cite as: | arXiv:2610.38398 [cs.AI] |
| (or arXiv:2610.38398v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.38398 arXiv-issued DOI via DataCite |
Submission history
From: Zuyao Xu [view email]
[v1]
Wed, 28 Oct 2026 07:41:23 UTC (1,569 KB)
来源：arXiv cs.AI · arxiv.org