Network design evolves for autonomous agents as unique entities
Agentic Communication Networks: When Agents Become Network Entities
Networking and Internet Architecture
Summary
Traditional computer networks treat devices as simple endpoints that send and receive data. The authors highlight that autonomous agents—software that can act independently—are becoming more active participants in networks, not just data sources. They propose a new way to design networks where these agents are recognized as distinct entities with their own identities, goals, and tasks. This approach helps networks better understand and coordinate the complex interactions and collaborations among multiple agents and services.
What this means in practice
- •For network architects: Design networks that treat autonomous agents as distinct entities with explicit identity and policy control to support complex coordinated tasks.
- •For cloud platform engineers: Build middleware to coordinate tasks and policies across multiple autonomous agents and distributed services within heterogeneous infrastructures.
A position paper. It proposes an approach and reports no results.
Authors
Renwei Li, Biwei Li, Nadjib Aitsaadi, Tarik Taleb, Cedric Westphal, Tao Huang, Luca Foschini, Zuqing Zhu
Abstract
Autonomous agents are moving from application-layer components to active participants in networked systems. They not only generate traffic but also perceive context, express intent, invoke services, coordinate with other agents, and act under task, policy, and resource constraints. This evolution exposes a mismatch between emerging agentic interactions and conventional endpoint- and traffic-centric network abstractions. This white paper introduces Agentic Communication Networks (ACN) as a network-centric paradigm for the time when agents become first-order network entities. At its core, ACN reshapes networking around three fundamental aspects. First, agents are represented as identifiable and governable network entities with explicit identity, authority, and lifecycle. Second, agentic services are expressed through intent, capability, context, policy, and task state, allowing the network to capture what an agent seeks to accomplish and under what conditions. Third, agentic execution becomes an explicit network concern as tasks involve multiple agents, services, tools, and distributed capabilities across heterogeneous infrastructures. Based on these shifts, the paper defines the scope, principles, architecture, and research directions of ACN, positioning it as a networking foundation for autonomous agent ecosystems.