The rapid evolution of wireless networks presents unprecedented challenges in managing diverse wireless tasks. These challenges underscore the need for AI-native solutions in next-generation networks. In this article, we propose WirelessAgent, a novel framework that harnesses large language models (LLMs) to create autonomous AI agents for diverse wireless network tasks. We first define a general framework for WirelessAgent, supported by key components and principles in AI agents. Then, we introduce a basic usage to implement the WirelessAgent based on agentic workflows and the LangGraph architecture. We demonstrate the effectiveness of WirelessAgent through a comprehensive case study on the network slicing task. Our numerical results show that WirelessAgent achieves 44.4% higher bandwidth utilization than the Prompt-based method, while performing only 4.3% below the Rule-based optimality. Notably, WirelessAgent delivers near-optimal network throughput across diverse network scenarios. These underscore the framework's potential for intelligent and autonomous control in next-generation networks. The code is available at https://github.com/jwentong/WirelessAgent_R1.

The rapid evolution of wireless technologies and the growing complexity of network infrastructures necessitate a paradigm shift in how communication networks are designed, configured, and managed. Recent advancements in large language models (LLMs) have sparked interest in their potential to revolutionize wireless communication systems. However, existing studies on LLMs for wireless systems are limited to a direct application for telecom language understanding. To empower LLMs with knowledge and expertise in the wireless domain, this paper proposes WirelessLLM, a comprehensive framework for adapting and enhancing LLMs to address the unique challenges and requirements of wireless communication networks. We first identify three foundational principles that underpin WirelessLLM: knowledge alignment, knowledge fusion, and knowledge evolution. Then, we investigate the enabling technologies to build WirelessLLM, including prompt engineering, retrieval augmented generation, tool usage, multi-modal pre-training, and domain-specific fine-tuning. Moreover, we present three case studies to demonstrate the practical applicability and benefits of WirelessLLM for solving typical problems in wireless networks. Finally, we conclude this paper by highlighting key challenges and outlining potential avenues for future research.

Within the realm of rapidly advancing wireless sensor networks (WSNs), distributed detection assumes a significant role in various practical applications. However, critical challenge lies in maintaining robust detection performance while operating within the constraints of limited bandwidth and energy resources. This paper introduces a novel approach that combines model-driven deep learning (DL) with binary quantization to strike a balance between communication overhead and detection performance in WSNs. We begin by establishing the lower bound of detection error probability for distributed detection using the maximum a posteriori (MAP) criterion. Furthermore, we prove the global optimality of employing identical local quantizers across sensors, thereby maximizing the corresponding Chernoff information. Subsequently, the paper derives the minimum MAP detection error probability (MAPDEP) by implementing identical binary probabilistic quantizers across the sensors. Moreover, the paper establishes the equivalence between utilizing all quantized data and their average as input to the detector at the fusion center (FC). In particular, we derive the Kullback-Leibler (KL) divergence, which measures the difference between the true posterior probability and output of the proposed detector. Leveraging the MAPDEP and KL divergence as loss functions, the paper proposes model-driven DL method to separately train the probability controller module in the quantizer and the detector module at the FC. Numerical results validate the convergence and effectiveness of the proposed method, which achieves near-optimal performance with reduced complexity for Gaussian hypothesis testing.

Host Intrusion Detection System (HIDS) is an important research topic in the field of cyberspace security. With the explosion in the number of malicious attacks in recent years, machine learning-based detection method is now the most common and efficient approach. While traditional centralized machine learning needs to transmit data to the central server for training, which not only requires the central server to have large computing resources, but also causes problems such as sensitive data leakage and communication overhead. As a distributed machine learning paradigm, Federated Learning (FL) can achieve multi-party collaborative training and aggregate a unified global model without data sharing, which can well alleviate these problems. It is worth noting that existing studies on the use of FL in HIDS are all conducted in the scenario where the data is independent and identically distributed (IID). However, due to the different context of hosts, the data generated by hosts is usually non-independent and identically distributed (Non-IID) in reality. Therefore, We investigate the impact of Non-IID data with different skew levels on FL in HIDS. On this basis, we propose a data augmentation FL algorithm based on Synthetic Minority Over-Sampling Technique (SMOTE) to reduce the impact of Non-IID data. We also develop a data collection module using extended Berkeley Packet Filter (eBPF) technology to collect a dataset for experiments. Experimental results show that our proposed FL algorithm can effectively improve the performance of HIDS under Non-IID data.

This paper studies the energy efficiency (EE) of two-way channels operating in the full-duplex (FD) mode. The residual self-interference (RSI) and self-interference cancellation (SIC) power are modeled as linear functions over the transmission power. The EE maximization problem for the considered FD mode with individual spectral efficiency (SE) constraint is formulated, and the corresponding optimal power allocation is derived by using fractional programming. Then, we further maximize the EE with sum SE constraint and the closed-form expression of this maximum EE is derived. Somehow surprisingly, numerical results show that the FD mode beats the half-duplex (HD) mode when the distance between the two transceivers is relatively large.