Rydberg atomic receivers (RARs) represent an emerging quantum sensing platform that offers extraordinary sensitivity in the detection of radio frequency (RF) signals. Its immunity to circuit thermal noise offers significant application potential in signal source localization scenarios with extremely high path loss. In this work, we develop an RAR-integrated low Earth orbit (LEO) satellite localization system that supports both instantaneous single-satellite single-antenna localization and high-accuracy multisatellite localization. In particular, this work, for the first time, derives the quantum spatially encoded nonstationary effect (QSENSE), through which the RAR can simultaneously measure both the angle of arrival (AoA) and Doppler shift, thereby doubling the spatial information diversity. As a result, even a single satellite equipped with a single RAR can achieve instantaneous 2-D localization (latitude and longitude), while two RAR-equipped satellites enable full 3-D localization. Simulation results show that, at an orbital altitude of 560 km with a transmit power of only 7 dBm, the proposed method achieves localization accuracy of up to 100 m, significantly outperforming conventional antennas in both accuracy and the required number of satellites.

With the growing demand for computation-intensive applications, multi-access edge computing (MEC) has emerged as a critical paradigm that decentralizes computation and storage by bringing resources closer to users. As distributed computing undergoes ongoing development propelled by the advancements in the Internet of Things (IoT) and mobile communication technologies, the issue of edge node cooperation and resource sharing needs to be investigated. In this paper, the issue of edge node cooperation and resource sharing is modeled as a two-layer framework. More specifically, in the lower layer, a heuristic matching algorithm between users and edge nodes is developed, and a resource sharing algorithm among edge nodes in the same coalition is proposed. In the upper layer, a centralized coalition formation algorithm is designed based on the Hungarian method, and then we further define the coalition rules among edge nodes and propose a distributed coalition formation algorithm. Simulation results demonstrate that the proposed algorithms reduce the network cost effectively compared with non-cooperative schemes. Moreover, we analyze the impact of various network parameters on the network cost, thereby providing insights for future optimization and development in MEC networks.

Renewable energy has become a viable alternative to fossil fuels owing to its environmental benefits. However, its inherent uncertainty pose significant challenges. Demand response (DR) mechanisms have been developed to address these issues, facilitating renewable energy integration through consumer-side flexible resources. However, these mechanisms often affect consumer satisfaction, necessitating precise measurement and control of these impacts. In this article, we propose a two-stage electricity trading and load dispatch optimization model aimed at reducing carbon emission by promoting renewable energy accommodation, and the proposed optimization model takes into account multicategory energy consumer satisfaction. We begin by classifying consumers into distinct categories and designing tailored satisfaction functions that reflect their unique power consumption pReferences. The electricity trading and load dispatch processes are formulated as a two-stage optimization problem, which is then transformed into Markov decision processes (MDPs). A model-free framework applying two state-of-the-art deep reinforcement learning (DRL) algorithms is proposed to solve the optimization problem without requiring complex environmental modeling and prior knowledge. Numerical results demonstrate that the proposed framework outperforms benchmark algorithms regarding both consumer satisfaction preservation and carbon emission reduction.

The low-altitude intelligent networks (LAINs) emerge as a promising architecture for delivering low-latency and energy-efficient edge intelligence in dynamic and infrastructure-limited environments. By integrating unmanned aerial vehicles (UAVs), aerial base stations, and terrestrial base stations, LAINs can support mission-critical applications such as disaster response, environmental monitoring, and real-time sensing. However, these systems face key challenges, including energy-constrained UAVs, stochastic task arrivals, and heterogeneous computing resources. To address these issues, we propose an integrated air-ground collaborative network and formulate a time-dependent integer nonlinear programming problem that jointly optimizes UAV trajectory planning and task offloading decisions. The problem is challenging to solve due to temporal coupling among decision variables. Therefore, we design a hierarchical learning framework with two timescales. At the large timescale, a Vickrey-Clarke-Groves auction mechanism enables the energy-aware and incentive-compatible trajectory assignment. At the small timescale, we propose the diffusion-heterogeneous-agent proximal policy optimization, a generative multi-agent reinforcement learning algorithm that embeds latent diffusion models into actor networks. Each UAV samples actions from a Gaussian prior and refines them via observation-conditioned denoising, enhancing adaptability and policy diversity. Extensive simulations show that our framework outperforms baselines in energy efficiency, task success rate, and convergence performance.

Traditional multi-path routing schemes for Space-Air-Ground Integrated Networks (SAGINs) pose the prominent challenge in reducing energy consumption. To address this, we study the energy minimization problem in multi-path routing by jointly optimizing link assignment, storage allocation, power control, and network routing in SAGINs over dynamic topologies. We first propose a Two-scale Time-Expanded Graph (TTEG) model to capture both network topology changes in large-timescale slots and mission data transmission in small-timescale slots. Using this TTEG model, we formulate the studied problem into a Mixed-Integer Non-Linear Program (MINLP) to minimize total energy consumption. We then leverage the inherent structure of the MINLP to divide it into two smaller subproblems. These two subproblems are solved iteratively with information feedback between them, thereby determining an optimal solution to the original problem in a few iteration steps. Simulation results validate the correctness and efficiency of the proposed solution.

With the exponential growth of connected devices and the advent of 6G, embodied agentic artificial intelligence (AI) emerges as a transformative paradigm for next-generation wireless networks. In this study, we leverage it to aid uncrewed aerial vehicle (UAV)-assisted multi-access edge computing (MEC) to provide efficient and reliable computation offloading for resource-constrained ground users. To cope with dynamic task arrivals and limited resource availability, we propose a two-timescale optimization framework that simultaneously minimizes the average task completion delay while maintaining load balance among UAVs and ensuring a low task failure rate. For the long-term system configuration, we develop a hybrid K-means and Particle Swarm Optimization (HKPSO) algorithm to jointly optimize UAV deployment and user association. For the short-term resource management, we design a two-layer Deep Reinforcement Learning (DRL) architecture where each UAV acts as an embodied agent. A Masked Double Deep Q-Network (MDDQN) handles discrete transmission scheduling while a Softmax Twin Delayed Deep Deterministic Policy Gradient (STD3) algorithm manages continuous computation allocation. Extensive experiments demonstrate that our proposed framework outperforms the baseline algorithms, validating its effectiveness and practicality in dynamic multi-UAV MEC systems.

The proliferation of Multi-Access Edge Computing (MEC) has led to massive data generation. This imposes complex and dynamic requirements on task scheduling. Conventional Unmanned Aerial Vehicle (UAV) scheduling methods struggle with task diversity. They lack adaptability to stochastic environments. Large Language Models (LLMs) provide powerful reasoning capabilities, while Retrieval-Augmented Generation (RAG) facilitates external knowledge integration. In this paper, we propose a RAG-empowered LLM framework for UAV scheduling. Proposed framework aims to minimize energy consumption and completion steps while maximizing rewards. We formulate the problem as a Mixed-Integer Non-Linear Program (MINLP). It is decoupled into discrete task allocation and continuous motion control. Our proposed framework parses natural language instructions via LLMs. To reduce latency, we design an adaptive hierarchical retrieval mechanism. This mechanism adjusts retrieval quantity based on task novelty. Finally, we introduce a dynamic management mechanism for long-term operations. It uses knowledge sparsity and policy contribution to prevent knowledge base bloat. Experiments show that proposed framework significantly outperforms baselines in energy consumption, scheduling efficiency, and rewards. It achieves up to 31.0% lower energy consumption, 13.5% lower decision latency, and 20% lower knowledge storage. Notably, it exhibits superior robustness and generalization under stochastic environments.

With the rapid development of communication technologies such as 6G and the wide deployment of high-speed rail (HSR), intelligent transportation is becoming an important internet of things (IoT) application scenario that requires reliable and efficient support for heterogeneous services. Therefore, it is crucial to effectively optimize resource allocation for 6G heterogeneous services, to improve the system utility of HSR communication. This paper addresses the challenging resource allocation problem for eMBB/URLLC coexistence services in HSR scenarios. Specifically, it models the communication of 6G heterogeneous services in the airship-assisted HSR scenario and proposes a hybrid optimization problem that maximizes the matching success rate of URLLC users, the transmission rate and the fairness of eMBB users. By decomposing the problem into two-stage subproblems, this paper efficiently optimizes the allocation of RB for eMBB and blocklength for URLLC in MR-user stage, and adopt a contract-based one-to-many matching algorithm to solve the user matching problem. In airship-MR stage, the transmission rate difference between the two communication stages is transformed into a joint convex optimization problem to be solved. Simulation results validate the effectiveness of the proposed algorithm in improving user matching success rates and system utility. This paper provides an efficient and fair solution for allocating communication resources in 6G intelligent transportation IoT systems.

Uncrewed Aerial Vehicles (UAVs) are widely deployed across diverse applications due to their mobility and agility. Recent advances in Large Language Models (LLMs) offer a transformative opportunity to enhance UAV intelligence beyond conventional optimization-based and learning-based approaches. By integrating LLMs into UAV systems, advanced environmental understanding, swarm coordination, mobility optimization, and high-level task reasoning can be achieved, thereby allowing more adaptive and context-aware aerial operations. This survey systematically explores the intersection of LLMs and UAV technologies and proposes a unified framework that consolidates existing architectures, methodologies, and applications for UAVs. We first present a structured taxonomy of LLM adaptation techniques for UAVs, including pretraining, fine-tuning, Retrieval-Augmented Generation (RAG), and prompt engineering, along with key reasoning capabilities such as Chain-of-Thought (CoT) and In-Context Learning (ICL). We then examine LLM-assisted UAV communications and operations, covering navigation, mission planning, swarm control, safety, autonomy, and network management. After that, the survey further discusses Multimodal LLMs (MLLMs) for human-swarm interaction, perception-driven navigation, and collaborative control. Finally, we address ethical considerations, including bias, transparency, accountability, and Human-in-the-Loop (HITL) strategies, and outline future research directions. Overall, this work positions LLM-assisted UAVs as a foundation for intelligent and adaptive aerial systems.

Digital Twins (DTs) have been proposed for monitoring and decision-making of complex systems, without being in the presence of the target system. However, this capability typically requires non-trivial amounts of data from target devices. In the case of lunar orbit and surface operations, obtaining data takes place over bandwidth-constrained links with long propagation delays and intermittent connectivity. These limitations are already evident in emerging architectures such as NASA’s Artemis program, where continuous data streaming from lunar assets is not always feasible. This paper proposes TwinSync, a mission-aware networking framework for maintaining synchronized digital twin states over dynamic cislunar networks. The approach combines a Cislunar Network Twin (CNT), which predicts time-varying topology and communication opportunities, with an Age-of-Synchronization (AoS)-aware scheduling mechanism that prioritizes deadline-constrained updates. Consequently, TwinSync ensures that missioncritical Time-Triggered (TT) traffic is supported by design. Simulation results show that TwinSync achieves zero TT deadline violations for deadline-constrained traffic across all evaluated scenarios. It also improves overall network utilization compared to representative deep space networking schemes, demonstrating a shift from reactive best-effort networking to predictive, mission-aware operation, where critical objectives are guaranteed a priori. Extended stress testing reveals that TwinSync maintains delivery of Time-Triggered information even under highly constrained traffic rates, dynamic mission phase transitions, and degraded network conditions.

The pervasive threat of jamming attacks, particularly from adaptive jammers capable of optimizing their strategies, poses a significant challenge to the security and reliability of wireless communications. This paper addresses this issue by investigating anti-jamming communications empowered by an active reconfigurable intelligent surface. The strategic interaction between the legitimate system and the adaptive jammer is modeled as a Stackelberg game, where the legitimate user, acting as the leader, proactively designs its strategy while anticipating the jammer's optimal response. We prove the existence of the Stackelberg equilibrium and derive it using a backward induction method. Particularly, the jammer's optimal strategy is embedded into the leader's problem, resulting in a bi-level optimization that jointly considers legitimate transmit power, transmit/receive beamformers, and active reflection. We tackle this complex, non-convex problem by using a block coordinate descent framework, wherein subproblems are iteratively solved via convex relaxation and successive convex approximation techniques. Simulation results demonstrate the significant superiority of the proposed active RIS-assisted scheme in enhancing legitimate transmissions and degrading jamming effects compared to baseline schemes across various scenarios. These findings highlight the effectiveness of combining active RIS technology with a strategic game-theoretic framework for anti-jamming communications.

Visual-Language Models (VLMs), with their strong capabilities in image and text understanding, offer a solid foundation for intelligent communications. However, their effectiveness is constrained by limited token granularity, overlong visual token sequences, and inadequate cross-modal alignment. To overcome these challenges, we propose TaiChi, a novel VLM framework designed for token communications. TaiChi adopts a dual-visual tokenizer architecture that processes both high- and low-resolution images to collaboratively capture pixel-level details and global conceptual features. A Bilateral Attention Network (BAN) is introduced to intelligently fuse multi-scale visual tokens, thereby enhancing visual understanding and producing compact visual tokens. In addition, a Kolmogorov Arnold Network (KAN)-based modality projector with learnable activation functions is employed to achieve precise nonlinear alignment from visual features to the text semantic space, thus minimizing information loss. Finally, TaiChi is integrated into a multimodal and multitask token communication system equipped with a joint VLM-channel coding scheme. Experimental results validate the superior performance of TaiChi, as well as the feasibility and effectiveness of the TaiChi-driven token communication system.

This paper addresses the urgent question of how emerging telecommunication networks, particularly beyond 5G and 6G networks, can be designed and governed to support climate action while limiting their own environmental footprint. We provide a comprehensive and cross-disciplinary analysis of the role of telecommunications in climate change adaptation, mitigation, and sectoral decarbonization, going beyond existing studies that typically focus on isolated technologies or single application domains. We review international climate and telecom policy frameworks, evaluate emerging 5G/6G capabilities, and analyze regulatory pathways for green networks to assess how next-generation connectivity, AI-based energy optimization, remote monitoring systems, and renewable integration can reduce emissions and enhance network resilience. Our findings organize these developments into a novel three-pillar framework that 1) clarifies how telecommunications-enabled climate-smart solutions underpin adaptation through early warning systems, disaster response coordination and infrastructure resilience, 2) shows how they drive mitigation across smart buildings and cities, precision agriculture and smart power systems, and 3) identifies concrete levers, such as energy-aware network design, energy-efficient architectures and network automation, for reducing the carbon footprint of the sector itself. The resulting framework provides policymakers, infrastructure planners, and telecom operators with a structured foundation to align network evolution with climate targets and to shape future regulatory and standardization efforts around climate-smart connectivity.

Large language models (LLMs) (e.g., ChatGPT, GPT-4 and Sora) have fundamentally transformed our daily lives, catalyzing breakthroughs in natural language processing, computer vision and revolutionizing human-computer interactions. However, their transformative potential is hindered by immense computational resources required. To address this challenge, the integration of LLMs with edge-cloud computing has become a focal point in advancing the capabilities of artificial intelligence. This survey comprehensively exploits the landscape of edge-enhanced intelligence, specifically focusing on the synergy between LLMs and edge-cloud computing. We delve into the evolution of LLMs, architectural intricacies, and the computational challenges associated with deploying them in edge environments from the aspects of data, computing power, model training and inference. Furthermore, we exploit the bidirectional symbiotic relationship between edge-cloud computing and LLMs from two key aspects: edge-cloud computing empowered LLMs (Edge4LLMs) and LLMs driven edge-cloud computing (LLMs4Edge). After that, we examine the dynamic collaboration between edge-cloud computing and LLMs, highlighting the complementary roles in optimizing the efficiency, real-time, and scalability of intelligent applications. Through an extensive review of existing research and practical implementations, this survey offers insights into the current state of edge-enhanced intelligence, identifies key challenges, and proposes potential avenues for future research and development. This survey aims to provide a comprehensive understanding of the emerging paradigm of edge-enhanced intelligence for LLMs, thereby fostering informed discussions and inspiring advancements in this field.

The widespread adoption of wireless communication systems in both military and civilian applications has significantly advanced technological progress and social development across various industries. However, narrowband interference signals pose a significant challenge, severely disrupting the normal operation of wireless communication equipment. A major obstacle in existing narrowband interference detection lies in enhancing robustness under complex channel propagation conditions and diverse, dynamically changing types of interference. In view of those challenges, we propose a robustness-enhanced narrowband interference detection method by utilizing unlabeled data. The proposed detection network incorporates soft-shrink technology to isolate irrelevant signal features while adaptively extracting and fusing original and time-frequency features. The proposed method leverages the distribution characteristics of interference frequency bands to enhance model robustness in varying channel propagation environments. Additionally, we design a pseudo-label-based model tuning process to exploit the potential of unlabeled data, further enhancing the model’s robustness. Comparative experiments demonstrate the superiority of the proposed method against various baselines, as well as against configurations incorporating individual network modules.

Increasing demands for massive data transmission pose significant challenges to communication systems. Compared with traditional communication systems that focus on the accurate reconstruction of bit sequences, semantic communications (SemComs), which aim to deliver information connotation, are regarded as a key technology for sixth-generation (6G) mobile networks. Most current SemComs utilize an end-to-end (E2E) trained neural network (NN) for semantic extraction and interpretation, which lacks interpretability for further optimization. Moreover, NN-based SemComs assume that the application and physical layers of the protocol stack can be jointly trained, which is incompatible with current digital communication systems. To overcome those drawbacks, we propose a SemCom system that employs explicit semantic bases (Sebs) as the basic units to represent semantic connotations. First, a mathematical model of Sebs is proposed to build an explicit knowledge base (KB). Then, the Seb-based SemCom architecture is proposed, including both a communication mode and a KB update mode to enable the evolution of communication systems. Sem-codec and channel codec modules are designed specifically, with the assistance of an explicit KB for the efficient and robust transmission of semantics. Moreover, unequal error protection (UEP) is strategically implemented, considering communication intent and the importance of Sebs, thereby ensuring the reliability of critical semantics. In addition, a Seb-based SemCom protocol stack that is compatible with the fifth-generation (5G) protocol stack is proposed. To assess the effectiveness and compatibility of the proposed Seb-based SemComs, a case study focusing on an image-transmission task is conducted. The simulations show that our Seb-based SemComs outperform state-of-the-art works in learned perceptual image patch similarity (LPIPS) by over 20% under varying communication intents and exhibit robustness under fluctuating channel conditions, highlighting the advantages of the interpretability and flexibility afforded by explicit Sebs.

With the explosive advancement of unmanned aerial vehicles (UAVs), the security of efficient UAV networks has become increasingly critical. Owing to the open nature of its communication environment, illegitimate malicious UAVs (MUs) can infer the position of the source UAV (SU) by analyzing received signals, thus compromising the SU location privacy. To protect the SU location privacy while ensuring efficient communication with legitimate receiving UAVs (RUs), we propose an Active Reconfigurable Intelligent Surface (ARIS)-assisted covert communication scheme based on virtual partitioning and artificial noise (AN). Specifically, we design a novel ARIS architecture integrated with an AN module. This architecture dynamically partitions its reflecting elements into multiple sub-regions: one subset is optimized to enhance communication between the SU and RUs, while the other subset generates AN to interfere with the localization of the SU by MUs. We first derive the Cram & eacute;r-Rao Lower Bound (CRLB) for localization with received signal strength (RSS), based on which, we establish a joint optimization framework for communication enhancement and localization interference. Subsequently, we derive and validate the optimal ARIS partitioning and power allocation under average channel conditions. Finally, tailored optimization methods are proposed for the reflection precoding and AN design of the two partitions. Simulation results validate that, compared to baseline schemes, the proposed scheme significantly increases the localization error of MUs by approximately 37.65% with only a 3.69% reduction in the communication rate between the SU and RUs, thereby effectively protecting the SU location privacy.

The deep integration of the Internet of Things (IoT) and federated learning establishes a privacy-preserving distributed learning paradigm for edge intelligence. However, dynamic task flows introduce challenges including asynchronous updates, catastrophic forgetting, and privacy constraints that limit traditional methods. This paper proposes KG-AsyncFed, a Knowledge-Sensitivity and Generative Replay Synergized Asynchronous Federated Continual Learning framework. Key innovations include: 1) A knowledge sensitivity driven generation mechanism computing parameter sensitivity matrices through gradient inversion while quantifying cross-task parameter importance differences with mixed-norm fusion; 2) Staleness-aware asynchronous aggregation implementing an exponential decay weight allocation strategy to prioritize integration of resource-sufficient and low-latency client updates; 3) Privacy-preserving generative replay synthesizing historical task features via a dual-model collaborative distillation generator with Gaussian noise injection for differential privacy constraints. Extensive experiments on Non-IID CIFAR-100 and Tiny-ImageNet demonstrate KG-AsyncFed’s significant improvements in average accuracy and forgetting suppression. Ablation studies confirm the synergistic effectiveness of knowledge sensitivity guided generative replay and asynchronous aggregation. The framework provides an efficient and secure continual learning solution for dynamic edge scenarios including industrial predictive maintenance and smart healthcare.

We are honored to present this special issue of IEEE Communications Magazine on Large AI Models for Communications. As 5G continues to advance in terms of low latency, massive connectivity, and high data rates, the 6G vision of ubiquitous intelligence is accelerating the deep integration of communication technologies and artificial intelligence. Empowered by capabilities in perception, analogy, and reasoning, the new generation of Large AI Models (LAMs) can efficiently characterize complex communication environments, enhance system generalization and adaptation to previously unseen scenarios, and support more personalized services for end users. Nevertheless, the further development of this emerging paradigm still faces several critical bottlenecks, including the computational and energy burden caused by the deep coupling of LAMs and communication systems, the lack of effective collaboration mechanisms between large and lightweight models, and the relative scarcity of domain-specific knowledge bases, datasets, and evaluation benchmarks for communications. This special issue brings together sixteen representative contributions and systematically examines the key issues in the convergence and evolution of LAMs and communication systems from the perspectives of theoretical foundations, system design, and open challenges, with the aim of offering useful insights to both academia and industry.

Improving energy efficiency (EE) and mass connectivity is an essential component of 6G networks. To address these challenges, there is a need for AI-driven approaches to energy efficiency, that can also account for the possible coexistence of cell-free (CF) and holographic MIMO (HM)-enabled base stations (HM BSs). Those BSs must distribute their power to the users by accumulating power from the serving HM BSs, taking into account the age of services (AoS) of the HM BSs. For such a network, in this paper, an optimization problem is designed to maximize EE by considering total power consumption and achievable rate, which results in maximizing the signal-to-interference-plus-noise ratio (SINR) of the obtained signal, ensuring effective power distribution. A transformer-aided AI scheme is developed to solve the designed NP-hard problem by allocating the necessary power through aggregation from the desired serving HM BSs, guided by their AoS information, thereby serving users in both HM and CF networks. Simulation results show that the proposed transformer-aided AI scheme achieves aggregated power savings of 6.4% and 9%, aggregated SINR improvements of 8.36 dB and 8.37 dB, aggregated achievable rate enhancements of 5.67 bps/Hz and 5.69 bps/Hz, and aggregated EE improvements of 12.2% and 7.8%, in comparison to the long short-term memory and gated recurrent unit-based methods, correspondingly.