A Layered Protocol Architecture for the Internet of Agents

TL;DR

The paper addresses the limitations of current agent protocols and LLM context windows by proposing a two-layer IoA stack: Layer 8 (Agent Communication Layer) for syntactic, exchange-focused interoperability and Layer 9 (Agent Semantic Negotiation Layer) for formal semantic grounding via Shared Contexts. By separating syntax from meaning, the approach enables deterministic, scalable multi-agent collaboration and supports both transactional orchestration and distributed coordination. It builds on existing standards (A2A, MCP, SLIM) while introducing novel semantic negotiation, context governance, and security considerations, outlining a path from concept to prototype. The proposed framework aims to provide reliable, interoperable, and semantically correct agent interactions, unlocking the next generation of multi-agent systems beyond naive shared-context assumptions and ad-hoc payload negotiations.

Abstract

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, now being standardized via protocols like MCP. However, LLMs face fundamental limitations: their context windows cannot grow indefinitely, constraining 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 Negotiation 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. L9, which does not exist today, formalizes the meaning of communication, enabling agents to discover, negotiate, and lock a "Shared Context" -- a formal schema defining the concepts, tasks, and parameters relevant to their interaction. Together, these layers provide the foundation for scalable, distributed agent collaboration, enabling the next generation of multi-agentic systems.

Figures (1)

• Figure 1: Traditional OSI stack and our proposed network stack for agentic applications. We propose two new layers for agent communication (L8 and L9) above HTTP/2/3, which serves as the Application Transport layer (L7).