Tool-Aided Evolutionary LLM for Generative Policy Toward Efficient Resource Management in Wireless Federated Learning

Federated Learning (FL) enables distributed model training across edge devices in a privacy-friendly manner. However, its efficiency heavily depends on effective device selection and high-dimensional resource allocation in dynamic and heterogeneous wireless environments. Conventional methods demand a confluence of domain-specific expertise, extensive hyperparameter tuning, and/or heavy interaction cost. This paper proposes a Tool-aided Evolutionary Large Language Model (T-ELLM) framework to generate a qualified policy for device selection in a wireless FL environment. Unlike conventional optimization methods, T-ELLM leverages natural language-based scenario prompts to enhance generalization across varying network conditions. The framework decouples the joint optimization problem mathematically, enabling tractable learning of device selection policies while delegating resource allocation to convex optimization tools. To improve adaptability, T-ELLM integrates a sample-efficient, model-based virtual learning environment that captures the relationship between device selection and learning performance, facilitating subsequent group relative policy optimization. This concerted approach reduces reliance on real-world interactions, minimizing communication overhead while maintaining high-fidelity decision-making. Theoretical analysis proves that the discrepancy between virtual and real environments is bounded, ensuring the advantage function learned in the virtual environment maintains a provably small deviation from real-world conditions. Experimental results demonstrate that T-ELLM outperforms benchmark methods in energy efficiency and exhibits robust adaptability to environmental changes.

Koopman-Based Generalization of Deep Reinforcement Learning With Application to Wireless Communications

Deep Reinforcement Learning (DRL) is a key machine learning technology driving progress across various scientific and engineering fields, including wireless communication. However, its limited interpretability and generalizability remain major challenges. In supervised learning, generalizability is commonly evaluated through the generalization error using information-theoretic methods. In DRL, the training data is sequential and not independent and identically distributed (i.i.d.), rendering traditional information-theoretic methods unsuitable for generalizability analysis. To address this challenge, this paper proposes a novel analytical method for evaluating the generalizability of DRL. Specifically, we first model the evolution of states and actions in trained DRL algorithms as unknown discrete, stochastic, and nonlinear dynamical functions. Then, we employ a data-driven identification method, the Koopman operator, to approximate these functions, and propose two interpretable representations. Based on these interpretable representations, we develop a rigorous mathematical approach to evaluate the generalizability of DRL algorithms. This approach is formulated using the spectral feature analysis of the Koopman operator, leveraging the H_\infty norm. Finally, we apply this generalization analysis to compare the soft actor-critic method, widely recognized as a robust DRL approach, against the proximal policy optimization algorithm for an unmanned aerial vehicle-assisted mmWave wireless communication scenario.

Next-Generation Wireless: Tracking the Evolutionary Path of 6G Mobile Communication

The mobile communications industry is lighting-fast machinery, and discussions about 6G technologies have already begun. In this article, we intend to take the readers on a journey to discover 6G and its evolutionary stages. The journey starts with an overview of the technical constraints of 5G prompting the need for a new generation of mobile systems. The initial discussion is followed by an examination of the 6G vision, use cases, technical requirements, technology enablers, and potential network architecture. We conclude the discussion by reviewing the transformative opportunities of this technology in society, businesses and industries, along with the anticipated technological limitations of the network that will drive the development of further mobile generations. Our goal is to deliver a friendly, informative, precise, and engaging narrative that could give readers a panoramic overview of this important topic.

Multi-Task Semantic Communication With Graph Attention-Based Feature Correlation Extraction

Multi-task semantic communication can serve multiple learning tasks using a shared encoder model. Existing models have overlooked the intricate relationships between features extracted during an encoding process of tasks. This paper presents a new graph attention inter-block (GAI) module to the encoder/transmitter of a multi-task semantic communication system, which enriches the features for multiple tasks by embedding the intermediate outputs of encoding in the features, compared to the existing techniques. The key idea is that we interpret the outputs of the intermediate feature extraction blocks of the encoder as the nodes of a graph to capture the correlations of the intermediate features. Another important aspect is that we refine the node representation using a graph attention mechanism to extract the correlations and a multi-layer perceptron network to associate the node representations with different tasks. Consequently, the intermediate features are weighted and embedded into the features transmitted for executing multiple tasks at the receiver. Experiments demonstrate that the proposed model surpasses the most competitive and publicly available models by 11.4% on the CityScapes 2Task dataset and outperforms the established state-of-the-art by 3.97% on the NYU V2 3Task dataset, respectively, when the bandwidth ratio of the communication channel (i.e., compression level for transmission over the channel) is as constrained as 1 12 .

Distributed Traffic Control in Complex Dynamic Roadblocks: A Multi-Agent Deep RL Approach

Autonomous Vehicles (AVs) represent a transformative advancement in the transportation industry. These vehicles have sophisticated sensors, advanced algorithms, and powerful computing systems that allow them to navigate and operate without direct human intervention. However, AVs' systems still get overwhelmed when they encounter a complex dynamic change in the environment resulting from an accident or a roadblock for maintenance. The advanced features of Sixth Generation (6G) technology are set to offer strong support to AVs, enabling real-time data exchange and management of complex driving maneuvers. This paper proposes a Multi-Agent Reinforcement Learning (MARL) framework to improve AVs' decision-making in dynamic and complex Intelligent Transportation Systems (ITS) utilizing 6G-V2X communication. The primary objective is to enable AVs to avoid roadblocks efficiently by changing lanes while maintaining optimal traffic flow and maximizing the mean harmonic speed. To ensure realistic operations, key constraints such as minimum vehicle speed, roadblock count, and lane change frequency are integrated. We train and test the proposed MARL model with two traffic simulation scenarios using the SUMO and TraCI interface. Through extensive simulations, we demonstrate that the proposed model adapts to various traffic conditions and achieves efficient and robust traffic flow management. The trained model effectively navigates dynamic roadblocks, promoting improved traffic efficiency in AV operations with more than 70% efficiency over other benchmark solutions.

Science-Informed Deep Learning (ScIDL) With Applications to Wireless Communications

Given the extensive and growing capabilities offered by deep learning (DL), more researchers are turning to DL to address complex challenges in next-generation (xG) communications. However, despite its progress, DL also reveals several limitations that are becoming increasingly evident. One significant issue is its lack of interpretability, which is especially critical for safety-sensitive applications. Another significant consideration is that DL may not comply with the constraints set by physics laws or given security standards, which are essential for reliable DL. Additionally, DL models often struggle outside their training data distributions, which is known as poor generalization. Moreover, there is a scarcity of theoretical guidance on designing DL algorithms. These challenges have prompted the emergence of a burgeoning field known as science-informed DL (ScIDL). ScIDL aims to integrate existing scientific knowledge with DL techniques to develop more powerful algorithms. The core objective of this article is to provide a brief tutorial on ScIDL that illustrates its building blocks and distinguishes it from conventional DL. Furthermore, we discuss both recent applications of ScIDL and potential future research directions in the field of wireless communications.

Channel Twinning: An Enabler for Next-Generation Ubiquitous Wireless Connectivity

The emerging concept of channel twinning (CT) has great potential to become a key enabler of ubiquitous connectivity in next-generation (xG) wireless systems. By fusing multimodal sensor data, CT advocates a high-fidelity and low-overhead channel acquisition paradigm, which is promising to provide accurate channel prediction in cross-domain and high-mobility scenarios of ubiquitous xG networks. However, the current literature lacks a universal CT architecture to address the challenges of heterogeneous scenarios, data, and resources in xG networks, which hinders the widespread deployment and applications of CT. This article discusses a new modularized CT architecture to bridge the barriers to scene recognition, cooperative sensing, and decentralized training. Based on the modularized design of CT, universal channel modeling, multimodal cooperative sensing, and lightweight twin modeling are described. Moreover, this article provides a concise definition, technical features, and case studies of CT, followed by potential applications of CT-empowered ubiquitous connectivity and some issues requiring future investigations.

Generative AI for the Optimization of Next-Generation Wireless Networks: Basics, State-of-the-Art, and Open Challenges

Next-generation (xG) wireless networks, with their complex and dynamic nature, present significant challenges to using traditional optimization techniques. Generative AI (GAI) emerges as a powerful tool due to its unique strengths. Unlike traditional optimization techniques and other machine learning methods, GAI excels at learning from real-world network data, capturing its intricacies. This enables safe, offline exploration of various configurations and generation of diverse, unseen scenarios, empowering proactive, data-driven exploration and optimization for xG networks. Additionally, GAI's scalability makes it ideal for large-scale xG networks. This paper surveys how GAI-based models unlock optimization opportunities in xG wireless networks. We begin by providing a review of GAI models and some of the major communication paradigms of xG (e.g., 6G) wireless networks. We then delve into exploring how GAI can be used to improve resource allocation and enhance overall network performance. Additionally, we briefly review the networking requirements for supporting GAI applications in xG wireless networks. The paper further discusses the key challenges and future research directions in leveraging GAI for network optimization. Finally, a case study demonstrates the application of a diffusion-based GAI model for load balancing, carrier aggregation, and backhauling optimization in non-terrestrial networks, a core technology of xG networks. This case study serves as a practical example of how the combination of reinforcement learning and GAI can be implemented to address real-world network optimization problems.

Decentralized Federated Learning Over Imperfect Communication Channels

This paper analyzes the impact of imperfect communication channels on decentralized federated learning (D-FL) and subsequently determines the optimal number of local aggregations per training round, adapting to the network topology and imperfect channels. We start by deriving the bias of locally aggregated D-FL models under imperfect channels from the ideal global models requiring perfect channels and aggregations. The bias reveals that excessive local aggregations can accumulate communication errors and degrade convergence. Another important aspect is that we analyze a convergence upper bound of D-FL based on the bias. By minimizing the bound, the optimal number of local aggregations is identified to balance a trade-off with accumulation of communication errors in the absence of knowledge of the channels. With this knowledge, the impact of communication errors can be alleviated, allowing the convergence upper bound to decrease throughout aggregations. Experiments validate our convergence analysis and also identify the optimal number of local aggregations on two widely considered image classification tasks. It is seen that D-FL, with an optimal number of local aggregations, can outperform its potential alternatives by over 10% in training accuracy.

A Reconfigurable Subarray Architecture and Hybrid Beamforming for Millimeter-Wave Dual-Function-Radar-Communication Systems

Dual-function-radar-communication (DFRC) is a promising candidate technology for next-generation networks. By integrating hybrid analog-digital (HAD) beamforming into a multi-user millimeter-wave (mmWave) DFRC system, we design a new reconfigurable subarray (RS) architecture and jointly optimize the HAD beamforming to maximize the communication sum-rate and ensure a prescribed signal-to-clutter-plus-noise ratio for radar sensing. Considering the non-convexity of this problem arising from multiplicative coupling of the analog and digital beamforming, we convert the sum-rate maximization into an equivalent weighted mean-square error minimization and apply penalty dual decomposition to decouple the analog and digital beamforming. Specifically, a second-order cone program is first constructed to optimize the fully digital counterpart of the HAD beamforming. Then, the sparsity of the RS architecture is exploited to obtain a low-complexity solution for the HAD beamforming. The convergence and complexity analyses of our algorithm are carried out under the RS architecture. Simulations corroborate that, with the RS architecture, DFRC offers effective communication and sensing and improves energy efficiency by 83.4% and 114.2% with a moderate number of radio frequency chains and phase shifters, compared to the persistently- and fullyconnected architectures, respectively.