arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2602.13795cs.NI
收藏

Agent-OSI: 向去中心化的智能体互联网的分层协议栈

Agent-OSI: An Interoperability Architecture for Communication and Settlement in the Decentralized Internet of Agents

Shenzhen University(深圳大学);The Chinese University of Hong Kong(香港中文大学)

Wenxin Xu, Taotao Wang, Yihan Xia, Shengli Zhang, Soung Chang Liew

AI总结:

Agent-OSI提出了一种基于现有互联网的六层协议栈,旨在实现去中心化智能体网络的互操作性、信任和按使用付费结算。

摘要:

大语言模型(LLMs)正在加速从信息互联网向智能体互联网(IoA)的转变,其中自主实体发现服务、协商、执行任务并交换价值。然而,当今的智能体仍然局限于平台孤岛和专有接口,缺乏用于互操作性、信任和按使用付费结算的通用堆栈。本文提出了Agent-OSI,一个基于现有互联网的六层参考堆栈,用于去中心化的智能体网络。Agent-OSI结合了安全连接和A2A消息传递、去中心化身份和授权、结算和计量、可验证执行和溯源,以及语义互操作性用于编排。特别是,我们将HTTP 402(支付所需)视为应用层支付挑战(类似于HTTP 401用于认证),该挑战触发基于保证金的结算和可验证凭证(在我们的原型中通过区块链保证金实现),而不是引入新的网络层协议。我们实现了一个原型并评估了成本和延迟。结果表明,在保持协商和交付离链的同时,保留可验证结算可以将链上会话成本降低约51%,与标准Web3基线相比,在我们的原型设置中,区块链确认延迟往往不是生成工作负载的主要因素。

英文摘要:

Large Language Models (LLMs) are accelerating the shift from an Internet of information to an Internet of Agents (IoA), where autonomous entities discover services, negotiate, execute tasks, and exchange value. Yet today's agents are still confined to platform silos and proprietary interfaces, lacking a common stack for interoperability, trust, and pay-per-use settlement. This article proposes \textit{Agent-OSI}, a functional interoperability architecture for a decentralized IoA, whose core contribution is agent-to-agent (A2A) communication and a Web-compatible, backend-agnostic settlement protocol built on HTTP 402 (Payment Required); identity, verifiable execution, and semantic orchestration are treated as boundary layers with interfaces to existing standards. We treat HTTP 402 as an application-layer challenge-response primitive -- analogous to HTTP 401 for authentication -- whose settlement backend (escrow contract, payment channel, or signed off-chain receipt) is a pluggable choice, instantiated via a blockchain escrow in our prototype. We implement a prototype and evaluate its communication and settlement performance. Results show that, for generative workloads, end-to-end latency is dominated by task execution rather than settlement confirmation, and that keeping negotiation and delivery off the settlement backend reduces per-session settlement cost by approximately 51\% relative to a more on-chain baseline.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑