arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2511.19699cs.NIcs.AIcs.MA
收藏

面向智能体的分层协议架构

A Layered Protocol Architecture for the Internet of Agents

Cisco Research(思科研究)

Charles Fleming, Luca Muscariello, Vijoy Pandey, Ramana Kompella

AI总结:

本文提出分层协议架构,通过智能体通信层和语义层实现智能体协作,解决LLMs在内存和计算能力上的限制,推动多智能体系统的扩展。

摘要:

大型语言模型(LLMs)在性能提升和学习领域特定语言(DSLs)方面表现出色,包括API和工具接口。这种能力使AI代理能够执行初步计算并通过工具调用进行操作,现在通过如MCP等协议标准化。然而,LLMs面临根本性限制:其上下文窗口无法无限增长,限制了其内存和计算能力。智能体协作对于解决日益复杂的问题至关重要,类似于计算系统依赖不同类型的内存来扩展。

英文摘要:

Large Language Models (LLMs) can learn domain-specific languages such as APIs and tool interfaces, enabling agents that act through standardized protocols like MCP. But LLM context windows cannot grow indefinitely, so scaling beyond individual capacity requires agent collaboration: the "Internet of Agents" (IoA). Current network stacks (OSI, TCP/IP) were designed for data delivery, not semantic coordination, so we propose two new layers: an Agent Communication Layer (L8) that standardizes message envelopes, speech-act performatives, and interaction patterns; and an Agent Semantic Layer (L9) that negotiates a shared context, grounds and disambiguates content against it, and provides consensus primitives for population-scale coordination. On two real datasets and two LLMs, L9's schema-grounded disambiguation improves accuracy on ambiguous requests by 13--72 percentage points over blind guessing, at no added cost when disambiguation is not needed; an ablation shows this gain is schema-specific for open-domain QA but not for structured slot-filling, where the protocol's round-trip structure alone already suffices.

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。

↑