cs.NIMar 2, 2026

Federated Agentic AI for Wireless Networks: Fundamentals, Approaches, and Applications

Authors: Lingyi Cai, Yu Zhang, Ruichen Zhang, Yinqiu Liu, Tao Jiang, Dusit Niyato, Wei Ni, Abbas Jamalipour

Organizations: Research Center of 6G Mobile Communications, School of Cyber Science and Engineering, Huazhong University of Science and Technology, Wuhan, 430074, China · College of Computing and Data Science, Nanyang Technological University, Singapore · School of Engineering, Edith Cowan University, Perth, WA 6027, and the School of Computer Science and Engineering, University of New South Wales (UNSW), Sydney, NSW 2033, Australia · School of Electrical and Computer Engineering, University of Sydney, Australia · 

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

Agentic artificial intelligence (AI) presents a promising pathway toward realizing autonomous and self-improving wireless network services. However, resource-constrained, widely distributed, and data-heterogeneous nature of wireless networks poses significant challenges to existing agentic AI that relies on centralized architectures, leading to high communication overhead, privacy risks, and non-independent and identically distributed (non-IID) data. Federated learning (FL) has the potential to improve the overall loop of agentic AI through collaborative local learning and parameter sharing without exchanging raw data. This paper proposes new federated agentic AI approaches for wireless networks. We first summarize fundamentals of agentic AI and mainstream FL types. Then, we illustrate how each FL type can strengthen a specific component of agentic AI's loop. Moreover, we conduct a case study on using FRL to improve the performance of agentic AI's action decision in low-altitude wireless networks (LAWNs). Finally, we provide a conclusion and discuss future research directions.

Figures & tables

Fig. 1: Overview of a federated agentic learning architecture for wireless networks. FSL and FUL enables privacy-preserving perception from decentralized RF measurements and logs. FGL constructs short- and long-term memory from distributed knowledge graphs. FGenL refines domain-specific reasoning, including LLM fine-tuning and CoT optimization. FRL drives tool-augmented actions through collaboratively learned policies. These components form a unified perception–memory–reasoning–action loop for RF anomaly detection and anti-jamming in wireless environments.
Fig. 2: (Left): The case-study scenario of a jamming-resilient UAV swarm in the LAWNs. (Right): The overall workflow of the FRL for actions of UAV agents, illustrating perception of physical and communication states, SLM-assisted reasoning, tool-based action decision and self-reflection, local policy update, and federated policy aggregation.
Fig. 3: Jamming attack success rate and defense cost of FRL agentic AI and CRL agentic AI under different UAV swarm sizes. As the swarm size increases, the centralized coordination overhead at the GCS grows rapidly, making CRL difficult to scale beyond N=10; thus, results of CRL for larger swarm sizes are not included.
More in this topic

Wireless Communications

Wireless communications studies how information is sent over radio links and how networks manage signals, spectrum, and resources reliably.

See all 391 papers

Explore similar work

CardsList

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

    Mar 10, 2026Loc X. Nguyen, Ji Su Yoon, Huy Q. Le +6Federated Learning6G Networks

    Department of Computer Science and Engineering, Kyung Hee University, Yongin-si, Gyeonggi-do 17104, Republic of Korea. · Department of Artificial Intelligence, Kyung Hee University, Yongin-si, Gyeonggi-do 17104, Republic of Korea. · School of Computer Science, The University of Sydney, Australia +1

  2. Over-the-Air Federated Learning: Rethinking Edge AI Through Signal Processing

    Dec 3, 2025Seyed Mohammad Azimi-Abarghouyi, Carlo Fischione, Kaibin HuangFederated Learning AggregationCommunication-Efficient Distributed Training

    School of Electrical Engineering and Computer Science, KTH Royal Institute of Technology, Stockholm, Sweden · Department of Electrical and Electronic Engineering, The University of Hong Kong, Hong Kong SAR, China

  3. Over-the-Air Federated Learning in Heterogeneous Mobile Wireless Networks

    Sep 26, 2026Ming Xiang, Nicolò Michelusi, Yonina C. Eldar +1Over-the-Air Federated LearningFederated Learning Aggregation

    Northeastern University, Boston, MA, USA · Arizona State University, Tempe, AZ, USA · Weizmann Institute of Science, Rehovot, Israel