Agentic AI as a Network Control-Plane Intelligence Layer for Federated Learning over 6G

TL;DR

This paper introduces an Agentic AI framework as a control layer for federated learning over 6G networks, integrating network management with learning tasks to enhance performance under diverse conditions.

Contribution

It presents a novel agent-based system that manages federated learning and network resources jointly, using monitoring, optimization, and closed-loop evaluation for adaptive decision-making.

Findings

Effective client selection and resource allocation demonstrated

Improved model training efficiency under variable network conditions

Case study shows high performance of the proposed system

Abstract

The shift toward user-customized on-device learning places new demands on wireless systems: models must be trained on diverse, distributed data while meeting strict latency, bandwidth, and reliability constraints. To address this, we propose an Agentic AI as the control layer for managing federated learning (FL) over 6G networks, which translates high-level task goals into actions that are aware of network conditions. Rather than simply viewing FL as a learning challenge, our system sees it as a combined task of learning and network management. A set of specialized agents focused on retrieval, planning, coding, and evaluation utilizes monitoring tools and optimization methods to handle client selection, incentive structuring, scheduling, resource allocation, adaptive local training, and code generation. The use of closed-loop evaluation and memory allows the system to consistently refine its decisions, taking into account varying signal-to-noise ratios, bandwidth conditions, and device capabilities. Finally, our case study has demonstrated the effectiveness of the Agentic AI system's use of tools for achieving high performance.