Tool Use as Action: Towards Agentic Control in Mobile Core Networks
2026-05-04 • Networking and Internet Architecture
Networking and Internet Architecture
AI summaryⓘ
The authors explore how Artificial Intelligence (AI) can be integrated into future 6G mobile networks to make them smarter and more autonomous. They propose using AI agents that communicate via special protocols to manage network tasks more efficiently. Their prototype focuses on how these AI agents interact with network tools and measure delays in completing tasks. This study shows a step toward AI-driven mobile networks that can handle complex goals automatically.
6GArtificial Intelligenceagentic AImobile core networkModel Context Protocol (MCP)Agent2Agent (A2A) protocolnetwork autonomyintent-based networkinglatency analysis
Authors
Purna Sai Garigipati, Onur Ayan, Kishor Chandra Joshi, Xueli An
Abstract
Artificial Intelligence (AI) will play an essential role in 6G. It will fundamentally reshape the network architecture itself and drive major changes in the design of network entities, interfaces, and procedures. The adoption of agentic AI in next-generation networks is expected to enhance network intelligence and autonomy through agents capable of planning, reasoning, and acting, while also opening up new business opportunities. Under this vision, existing network functions are expected to evolve into AI-enabled agents and tools that deliver both connectivity and beyond-connectivity services. As an initial attempt to move toward this vision, this paper presents a tool-based interface design and an experimental prototype that are based on agentic AI for the mobile core network, with the Model Context Protocol (MCP) and the Agent2Agent (A2A) protocol as foundational protocols. MCP is selected to design the interface between the agent and network tools, and the A2A protocol is used for message exchange between AI agents. In such an experimental setup, we analyze packet-level message flows between the agents, tools, and network functions and break down the latency of end-to-end operations, starting from the prompt injection until the completion of the input task. This work demonstrates how an AI agent-based core network combined with network-specific tools can be utilized in next generation mobile systems to execute intent-based tasks.