This paper investigates the integration of large language models (LLMs) as reasoning agents in repeated spectrum auctions within heterogeneous networks (HetNets). While auction-based mechanisms have been widely employed for efficient resource allocation, most prior works assume one-shot auctions, static bidder behavior, and idealized conditions. In contrast to traditional formulations where base station (BS) association and power allocation are centrally optimized, we propose a distributed auction-based framework in which each BS independently conducts its own multi-channel auction, and user equipments (UEs) strategically decide both their association and bid values. Within this setting, UEs operate under budget constraints and repeated interactions, transforming resource allocation into a long-term economic decision rather than a one-shot optimization problem. The proposed framework enables the evaluation of diverse bidding behaviors -from classical myopic and greedy policies to LLM-based agents capable of reasoning over historical outcomes, anticipating competition, and adapting their bidding strategy across episodes. Simulation results reveal that the LLM-empowered UE consistently achieves higher channel access frequency and improved budget efficiency compared to benchmarks. These findings highlight the potential of reasoning-enabled agents in future decentralized wireless networks markets and pave the way for lightweight, edge-deployable LLMs to support intelligent resource allocation in next-generation HetNets.

This paper unveils the underlying tri-polarization effect in distributed multiple-input multiple-output (MIMO) systems with dual-polarized access points (APs) and tri-polarized users. Specifically, APs and users follow independent Poisson point processes, and the multi-polarized multi-user channel is modeled by the dyadic Green’s function. The eigenvalue analysis reveals that the spatial distribution of the APs and the AP-user height difference contribute to the excitation of an additional polarization dimension. The varying propagation angles of signals from multiple spatially distributed APs lead to angular spread, while the height difference further amplifies this effect by reducing signal coherence, thereby facilitating the excitation of the additional polarization dimension. Based on the derived channel eigenvalues, the capacity gap between tri-polarized receivers and baseline dual-polarized receivers is quantified, as well as the energy projection into the additional polarization dimension. Simulation results demonstrate that distributed MIMO can effectively excite the additional polarization, increasing the effective degrees of freedom by up to 1.5 times compared with dual-polarized configurations. Moreover, energy dispersion across three polarization dimensions reduces capacity by about 30% for dual-polarized receivers. In contrast, tri-polarized receivers fully capture the additional polarization gain and thereby eliminate this loss. The excitation is maximized at an average AP-user elevation angle of 45°, where the energy projection into the additional polarization dimension reaches 20%. Finally, the close agreement between theoretical derivations and simulations provides practical guidance for antenna deployment and a new paradigm for exploiting polarization diversity.

Post-Training Quantization (PTQ) and Low-Rank Adaptation (LoRA) constitute the standard pipeline for efficient Large Language Model (LLM) deployment. However, applying them sequentially poses a problem: PTQ often leaves behind random noise that is spread out (across the model's weights) in a way LoRA can't easily fix, meaning that LoRA ends up wasting its limited capacity trying to fix uncorrectable noise instead of improving task performance. In this paper, we propose ProjQ, a novel framework for constraining quantization noise to the low-rank manifold via orthogonal subspace projection. We derive an efficient alternating algorithm that shapes the quantization noise into a low-rank structure, effectively offloading dominant error components to the subsequent adapter while minimizing the residual error in the orthogonal "uncorrectable" subspace. Our theoretical analysis demonstrates that ProjQ preserves strictly greater model plasticity for downstream tasks compared to standard PTQ. Extensive experiments on LLaMA-2, Qwen2.5 and Qwen3 confirm that ProjQ consistently outperforms existing methods in both quantization error compensation and downstream task fine-tuning, achieving up to 2× lower evaluation loss for compensation and matching the performance of standard 4-bit baselines on language modeling tasks with only 3 bits. The code is available on https://github.com/yy9301/ProjQ .

With its capability to obtain a good tradeoff between complexity and performance, regularized zero-forcing (RZF) has been widely investigated to enhance the physical layer security. However, the associated reliability performance, i.e., secrecy outage probability (SOP), is not yet available in the literature. In this paper, we characterize the secrecy performance of RZF in the multi-user, downlink multiple-input single-output system. For this purpose, we first set up a central limit theorem for the joint distribution of users’ signal-to-interference-plus-noise ratio and eavesdropper’s signal-to-noise ratio by leveraging random matrix theory. The result is then utilized to obtain a closed-form approximation for the ergodic secrecy rate and SOP of three typical scenarios: the case with only external Eves, the case with only internal Eves, and that with both. The derived results are then used to evaluate the percentage of users in secrecy outage and the required number of transmit antennas to achieve a positive secrecy rate. It is shown that, with equally-capable Eves, the secrecy loss caused by external Eves is higher than that caused by internal Eves. Numerical simulations validate the accuracy of the theoretical results and demonstrate the advantage of RZF over other linear transmitters such as ZF.

Generative models have shown immense potential for wireless communication by learning complex channel data distributions. However, the iterative denoising process associated with these models imposes a significant challenge in latency-sensitive wireless communication scenarios, particularly in channel estimation. To address this challenge, we propose a novel solution for one-step generative channel estimation. Our approach bypasses the time-consuming iterative steps of conventional models by directly learning the average velocity field. Through extensive simulations, we validate the effectiveness of our proposed method over existing state-of-the-art diffusion-based approach. Specifically, our scheme achieves a normalized mean squared error up to 2.65 dB lower than the diffusion method and reduces latency by around 90

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.

Telecommunications is a high-leverage domain for large language model (LLM)-based reasoning because routine engineering workflows require joint grounding in normative specifications, operational telemetry, vendor-specific fault evidence, and exact RF/network calculations. However, current LLM integration in telecom remains bottlenecked by a two-sided capability gap: generic reasoners often lack telecom-specific grounding, while domain-specific telecom LLMs remain limited in structured, multi-step reasoning. To bridge this gap, we release TelecomGPT-R1-9B, a unified open-source telecom reasoner that ranks top-performing on the GSMA open telco leaderboard. Specifically, we curate a 67,427-example supervised fine-tuning (SFT) corpus organized around four complementary reasoning axes: protocol, knowledge, modeling, and fault. The corpus is built from axis-matched public web sources and enhanced through axis-specific chain-of-thought (CoT) generation and prefix-continuation self-validation. Starting from Qwen3.5-9B, we further develop a two-stage post-training recipe. First, multi-teacher low-rank adaptation (LoRA)-based SFT injects telecom knowledge and induces axis-specific reasoning formats. Second, group relative policy optimization (GRPO), stabilized by decoupled clip and dynamic sampling policy optimization (DAPO), optimizes the policy using four axis-aligned binary verifier rewards. Across seven public telecom benchmarks, TelecomGPT-R1-9B ranks first among open-source telecom LLMs and achieves a seven-axis mean comparable to state-of-the-art closed-source frontier reasoners.

Large Language Models (LLMs) are increasingly used as high level controllers for autonomous Unmanned Aerial Vehicle (UAV) missions. However, existing evaluations rarely assess whether such agents remain safe, protocol compliant, and effective under realistic next generation networking constraints. This paper introduces α^3-Bench, a benchmark for evaluating LLM driven UAV autonomy as a multi turn conversational reasoning and control problem operating under dynamic 6G conditions. Each mission is formulated as a language mediated control loop between an LLM based UAV agent and a human operator, where decisions must satisfy strict schema validity, mission policies, speaker alternation, and safety constraints while adapting to fluctuating network slices, latency, jitter, packet loss, throughput, and edge load variations. To reflect modern agentic workflows, α^3-Bench integrates a dual action layer supporting both tool calls and agent to agent coordination, enabling evaluation of tool use consistency and multi agent interactions. We construct a large scale corpus of 113k conversational UAV episodes grounded in UAVBench scenarios and evaluate 17 state of the art LLMs using a fixed subset of 50 episodes per scenario under deterministic decoding. We propose a composite α^3 metric that unifies six pillars: Task Outcome, Safety Policy, Tool Consistency, Interaction Quality, Network Robustness, and Communication Cost, with efficiency normalized scores per second and per thousand tokens. Results show that while several models achieve high mission success and safety compliance, robustness and efficiency vary significantly under degraded 6G conditions, highlighting the need for network aware and resource efficient LLM based UAV agents. The dataset is publicly available on GitHub : https://github.com/maferrag/AlphaBench

Terahertz (THz) communication combined with ultra-massive multiple-input multiple-output (UM-MIMO) technology is promising for 6G wireless systems, where fast and precise direction-of-arrival (DOA) estimation is crucial for effective beamforming. However, finding DOAs in THz UM-MIMO systems faces significant challenges: while reducing hardware complexity, the hybrid analog-digital (HAD) architecture introduces inherent difficulties in spatial information acquisition the large-scale antenna array causes significant deviations in eigenvalue decomposition results; and conventional two-dimensional DOA estimation methods incur prohibitively high computational overhead, hindering fast and accurate realization. To address these challenges, we propose a hybrid dynamic subarray (HDS) architecture that strategically divides antenna elements into subarrays, ensuring phase differences between subarrays correlate exclusively with single-dimensional DOAs. Leveraging this architectural innovation, we develop two efficient algorithms for DOA estimation: a reduced-dimension MUSIC (RD-MUSIC) algorithm that enables fast processing by correcting large-scale array estimation bias, and an improved version that further accelerates estimation by exploiting THz channel sparsity to obtain initial closed-form solutions through specialized two-RF-chain configuration. Furthermore, we develop a theoretical framework through Cramér-Rao lower bound analysis, providing fundamental insights for different HDS configurations. Extensive simulations demonstrate that our solution achieves both superior estimation accuracy and computational efficiency, making it particularly suitable for practical THz UM-MIMO systems.

Stacked intelligent metasurfaces (SIMs) have emerged as a powerful paradigm for wave-domain signal processing, enabling fine-grained control over electromagnetic (EM) propagation in next-generation wireless systems. However, conventional multi-layer SIMs often suffer from excessive structural complexity, high computational overhead, and significant power attenuation across layers, limiting their performance. In this paper, we first characterize SIMs from the perspectives of functionality, application, and layer configuration, revealing the inherent trade-offs between signal processing flexibility and power efficiency. Then, two representative 2-layer architectures, the meta-fiber-connected SIM (MF-SIM) and the flexible intelligent layered metasurface (FILM), are introduced, each advocating a distinct 2-layer SIM design philosophy. Moreover, we identify several open challenges in topology optimization for MF-SIM, shape control for FILM, and hybrid 2-layer architectures. Finally, case studies considering 2-layer MF-SIM and FILM assisted point-to-point multiple-input multiple-output (MIMO) and multi-user communication systems validate that properly designed 2-layer SIMs can significantly reduce power loss and optimization burden while maintaining good signal processing performance, offering a promising pathway toward practical SIM-enabled 6G systems.

The growing demand for maritime broadband services exposes the limitations of conventional satellite–ground systems, which often fail to jointly optimize spatial–temporal resources, computation costs, and the trade-offs between energy and information freshness. To address these challenges, we develop a physics-aware system model for near-shore Space-Air-Ground-Sea Integrated Networks (SAGSIN), capturing realistic maritime channels, Poisson task arrivals, Age of Information (AoI), and energy consumption. Based on this model, we propose a AI-enabled dual-timescale framework based on heterogeneous Mixture-of-Experts (MoE). Specifically, the framework operations are formulated as a two-agent Markov decision process: the long-slot agent determines satellite beam-hopping coverage, while the short-slot agent jointly optimizes per-slot task offloading, UAV deployment, and resource allocation. Both agents employ MoE policies with Top-K gating. Simulation results validate that the proposed framework achieves superior AoI–energy trade-offs compared with baseline methods, highlighting the potential of AI-driven autonomy in next-generation network orchestration.

Stacked intelligent metasurfaces (SIMs), which integrate multiple programmable metasurface layers, have recently emerged as a promising technology for advanced wave-domain signal processing. SIMs benefit from flexible spatial degree-of-freedom (DoF) while reducing the requirement for costly radio-frequency (RF) chains. However, current state-of-the-art SIM designs face challenges such as complex phase shift optimization and energy attenuation from multiple layers. To address these aspects, we propose incorporating meta-fibers into SIMs, with the aim of reducing the number of layers and enhancing the energy efficiency. First, we introduce a meta-fiber-connected 2-layer SIM that exhibits the same flexible signal processing capabilities as conventional multi-layer structures, and explains the operating principle. Subsequently, we formulate and solve the optimization problem of minimizing the mean square error (MSE) between the SIM channel and the desired channel matrices. Specifically, by designing the phase shifts of the meta-atoms associated with the transmitting-SIM and receiving-SIM, a non-interference system with parallel subchannels is established. In order to reduce the computational complexity, a closed-form expression for each phase shift at each iteration of an alternating optimization (AO) algorithm is proposed. We show that the proposed algorithm is applicable to conventional multi-layer SIMs. The channel capacity bound and computational complexity are analyzed to provide design insights. Finally, numerical results are illustrated, demonstrating that the proposed two-layer SIM with meta-fiber achieves over a 25% improvement in channel capacity while reducing the total number of meta-atoms by 59% as compared with a conventional seven-layer SIM.

Environment sensing and fusion via onboard sensors are envisioned to be widely applied in future autonomous driving networks. This paper considers a vehicular system with multiple self-driving vehicles that is assisted by multi-access edge computing (MEC), where image data collected by the sensors is offloaded from cellular vehicles to the MEC server using vehicle-to-infrastructure (V2I) links. Sensory data can also be shared among surrounding vehicles via vehicle-to-vehicle (V2V) communication links. To improve spectrum utilization, the V2V links may reuse the same frequency spectrum as the V2I links, which may cause severe interference. To tackle this issue, we leverage reconfigurable intelligent computational surfaces (RICSs) to jointly enable V2I reflective links and mitigate interference appearing at the V2V links. Considering the limitations of traditional algorithms in addressing this problem, such as the assumption of quasi-static channel state information, which restricts their ability to adapt to dynamic environmental changes and leads to poor performance under frequently varying channel conditions, in this paper, we formulate the problem at hand as a Markov game. Our novel formulation is applied to time-varying channels subject to multi-user interference and introduces a collaborative learning mechanism among users. The considered optimization problem is solved via a driving safety-enabled multi-agent deep reinforcement learning (DS-MADRL) approach that capitalizes on the RICS presence. Our extensive numerical investigations showcase that the proposed reinforcement learning approach achieves faster convergence and significant enhancements in both data rate and driving safety, as compared to various state-of-the-art benchmarks.

In this correspondence, a novel integrated sensing and communication (ISAC) framework is proposed to accomplish data communication, vehicle positioning, and environment sensing simultaneously in a cellular vehicular network. By incorporating the vehicle positioning problem with the existing computational-imaging-based ISAC models, we formulate a special integrated sensing, communication, and positioning problem in which the unknowns are highly coupled. To mitigate the rank deficiency and make it solvable, we discretize the region of interest (ROI) into sensing and positioning pixels respectively, and exploit both the line-of-sight and non-line-of-sight propagation of the vehicles' uplink access signals. The resultant problem is shown to be a polynomial bilinear compressed sensing (CS) reconstruction problem, which is then solved by the alternating optimization (AO) algorithm to iteratively achieve symbol detection, vehicle positioning and environment sensing. Performance analysis and numerical results demonstrate the effectiveness of the proposed method

Large Language Models (LLMs) are rapidly transitioning from standalone conversational systems to autonomous agents that reason, plan, and interact with external tools. While this shift enables powerful applications in domains such as healthcare, finance, law, and software engineering, it also introduces new security and safety risks. Attacks such as prompt injection, jailbreak exploits, backdoor triggers, and multimodal adversarial inputs expose vulnerabilities not only at the model level but also across the broader agentic workflow. Existing defenses—ranging from input filtering and alignment reinforcement to runtime monitoring—remain fragmented and often fail to anticipate adaptive adversaries. Meanwhile, red teaming has emerged as a critical methodology for stress-testing these systems; however, current efforts lack standardization, comprehensive coverage across modalities, and integration with agent-specific contexts. This paper provides the first comprehensive survey of LLM agent security, synthesizing research on attack strategies, red teaming frameworks, evaluation suites, and defense mechanisms. We categorize automated and agentic red teaming approaches, highlight domain-specific vulnerabilities in code, web, and multimodal agents, and analyze defense strategies spanning prompt-level, decoding-time, runtime, backdoor, privacy-preserving, and multi-agent safeguards. Building on this synthesis, we outline key open challenges and future research directions, including the need for scalable defenses, standardized benchmarks, robustness against adaptive attacks, explainability, and secure integration of multi-agent workflows. Our findings aim to guide both researchers and practitioners in advancing robust, trustworthy, and resilient LLM-powered agents for safety-critical applications.

Future sixth-generation (6G) networks require high spectral efficiency (SE), massive connectivity, and stringent reliability under imperfect channel state information at the transmitter. Rate-splitting multiple access (RSMA) addresses part of this challenge by flexibly managing interference through common and private message streams, while fluid antenna systems (FAS) offer low-cost spatial diversity by dynamically reconfiguring antenna positions within a compact aperture. In this paper, we first classify FAS-enabled multiple access systems from the perspectives of FAS deployment, objectives, and antenna configuration, along with some comparisons with benchmark schemes, thereby exhibiting the inherent efficiency of FAS-RSMA. Moreover, we reveal the mutually enhancing mechanism between FAS and RSMA: FAS strengthens the weakest effective link and improves the beamforming design in RSMA, whereas RSMA turns FAS-induced spatial diversity into robust interference management under diverse channel conditions. In addition, we identify representative 6G scenarios and highlight major research challenges in joint beamforming-antenna position design, channel estimation, and hardware design. Furthermore, case studies quantify the gains of FAS-RSMA over the fixed-position antenna (FPA) system with RSMA and NOMA baselines, which validates that FAS-RSMA is a strong candidate for interference-limited access in 6G systems.

Proactive and agentic control in Sixth-Generation (6G) Open Radio Access Networks (O-RAN) requires control-grade prediction under stringent Near-Real-Time (Near-RT) latency and computational constraints. While Transformer-based models are effective for sequence modeling, their quadratic complexity limits scalability in Near-RT RAN Intelligent Controller (RIC) analytics. This paper investigates a post-Transformer design paradigm for efficient radio telemetry forecasting. We propose a quantum-inspired many-body state-space tensor network that replaces self-attention with stable structured state-space dynamics kernels, enabling linear-time sequence modeling. Tensor-network factorizations in the form of Tensor Train (TT) / Matrix Product State (MPS) representations are employed to reduce parameterization and data movement in both input projections and prediction heads, while lightweight channel gating and mixing layers capture non-stationary cross-Key Performance Indicator (KPI) dependencies. The proposed model is instantiated as an agentic perceive-predict xApp and evaluated on a bespoke O-RAN KPI time-series dataset comprising 59,441 sliding windows across 13 KPIs, using Reference Signal Received Power (RSRP) forecasting as a representative use case. Our proposed Linear Quantum-Inspired State-Space (LiQSS) model is 10.8x-15.8x smaller and approximately 1.4x faster than prior structured state-space baselines. Relative to Transformer-based models, LiQSS achieves up to a 155x reduction in parameter count and up to 2.74x faster inference, without sacrificing forecasting accuracy.

While stacked intelligent metasurfaces (SIMs) have demonstrated significant technical and cost advantages in multiuser scenarios, existing literature universally assumes ideal transceiver hardware. Addressing this gap, this paper investigates the design and optimization of a SIM-assisted multiuser downlink multiple-input single-output (MISO) system under practical transceiver hardware impairments (HWIs). To accurately capture distortion effects at both the base station (BS) and user equipment, we adopt an aggregate HWI model based on improper Gaussian statistics. The considered impairments include finite-resolution digital-to-analog converters (DACs), power amplifier (PA) nonlinearities, in-phase/quadrature (I/Q) imbalance, and other radio-frequency (RF) front-end non-idealities. We formulate a sum-rate (SR) maximization problem that jointly optimizes digital beamforming at the BS and multi-layer analog beamforming at the SIM. To tackle this highly non-convex optimization challenge, we propose a closed-form-based iterative algorithm that alternately updates BS and SIM beamforming with guaranteed convergence. Extensive simulations validate the effectiveness of the proposed algorithm, quantify the impact of different HWI sources, and demonstrate that SIM deployment significantly improves system robustness, mitigates HWI-induced performance degradation, and reduces DAC resolution requirements without substantial performance loss.

Large language models (LLMs) show strong potential for Intelligent Transportation Systems (ITS), particularly in tasks requiring situational reasoning and multi-agent coordination. These capabilities make them well suited for cooperative driving, where rule-based approaches struggle in complex and dynamic traffic environments. Intersection management remains especially challenging due to conflicting right-of-way demands, heterogeneous vehicle priorities, and vehicle-specific kinematic constraints that must be resolved in real time. However, existing approaches typically use LLMs as auxiliary components on top of signal-based systems rather than as primary decision-makers. Signal controllers remain vehicle-agnostic, reservation-based methods lack intent awareness, and recent LLM-based systems still depend on signal infrastructure. In addition, LLM inference latency limits their use in sub-second control settings. We propose LIDSA (LLM-Based Intent-Driven Speed Advisory), a signal-free cognitive arbitration framework for autonomous intersection management. LIDSA uses an LLM to reason over declared vehicle intents, incorporating priority classes, queue pressure, and energy preferences. We evaluate LIDSA against fixed-cycle control, SCATS, AIM, and GLOSA across varying traffic loads. Results show that LIDSA reduces mean control delay by up to 89.1