为AI代理协作设计分层通信架构，解决大模型记忆与计算瓶颈。
A Layered Protocol Architecture for the Internet of Agents
- 提出L8（通信层）与L9（语义层）新协议，规范代理间交互模式。
- 支持语义上下文协商、术语绑定与提示消歧，实现跨代理理解对齐。
- 适合构建可扩展的多智能体系统，尤其在复杂任务协同中优势明显。
大型语言模型（LLMs）展现出显著性能提升，并能学习领域特定语言（DSL），包括API和工具接口。这一能力催生了可通过工具调用执行初步计算并采取行动的AI代理，相关协议如MCP正趋于标准化。然而，LLMs存在根本局限：其上下文窗口无法无限增长，限制了记忆与计算能力。代理协作成为解决日益复杂问题的关键，类比于计算系统依赖多种内存实现扩展。所谓“智能体互联网”（IoA）即为支持代理通过分布式协作实现扩展的通信栈。现有网络架构（如OSI、TCP/IP）专为主机与进程间数据传输设计，不适用于具备语义理解的代理协作。为此，我们提出两个新层：代理通信层（L8）和代理语义层（L9）。L8规范通信结构，标准化消息封装、言语行为（如REQUEST、INFORM）及交互模式（如请求-回复、发布-订阅），基于MCP等协议。L9层则：（1）形式化语义上下文发现与协商；（2）通过绑定术语到语义上下文实现语义锚定；（3）对输入提示进行语义验证与歧义消解。此外，L9引入协调与共识原语，使代理能够就共享状态、集体目标与分布式信念达成一致。二者共同构成可扩展分布式代理协作的基础，推动下一代多智能体系统发展。
原文摘要 · Abstract (English)
Large Language Models (LLMs) have demonstrated remarkable performance improvements and the ability to learn domain-specific languages (DSLs), including APIs and tool interfaces. This capability has enabled the creation of AI agents that can perform preliminary computations and act through tool calling, which is now being standardized via protocols like MCP. However, LLMs face fundamental limitations: their context windows cannot grow indefinitely, restricting their memory and computational capacity. Agent collaboration emerges as essential for solving increasingly complex problems, mirroring how computational systems rely on different types of memory to scale. The "Internet of Agents" (IoA) represents the communication stack that enables agents to scale by distributing computation across collaborating entities. Current network architectural stacks (OSI and TCP/IP) were designed for data delivery between hosts and processes, not for agent collaboration with semantic understanding. To address this gap, we propose two new layers: an Agent Communication Layer (L8) and an Agent Semantic Layer (L9). L8 formalizes the structure of communication, standardizing message envelopes, speech-act performatives (e.g., REQUEST, INFORM), and interaction patterns (e.g., request-reply, publish-subscribe), building on protocols like MCP. The proposed L9 layer: (1) formalizes semantic context discovery and negotiation, (2) provides semantic grounding by binding terms to semantic context, and (3) semantically validates incoming prompts and performs disambiguation as needed. Furthermore, L9 introduces primitives for coordination and consensus, allowing agents to achieve alignment on shared states, collective goals, and distributed beliefs. Together, these layers provide the foundation for scalable, distributed agent collaboration, enabling the next generation of multi-agentic systems.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。