Tool Use as Action: Towards Agentic Control in Mobile Core Networks

2026-05-04

AI Summary

This work addresses the challenges of realizing intent-driven services in 6G mobile core networks by proposing an intelligent agent control architecture endowed with planning, reasoning, and execution capabilities. It pioneers the integration of the tool-use paradigm into mobile core networks, defining agent–network function interactions through the Model Context Protocol (MCP) and enabling multi-agent collaboration via the Agent2Agent (A2A) protocol. An end-to-end prototype system is implemented to demonstrate that AI agents can efficiently invoke domain-specific network tools to fulfill high-level intents. The study further quantifies packet-level message flows and end-to-end latency from prompt injection to task completion, providing empirical evidence for the feasibility and performance of agent-native network functions and advancing the evolution of core networks toward intelligent autonomy.

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.

Problem

• Agentic AI
• Mobile Core Networks
• Tool Use
• 6G
• Intent-based Networking

Innovation

• agentic AI
• tool use
• Model Context Protocol
• mobile core network
• intent-based networking