CR^2: Cost-Aware Risk-Controlled Routing for Wireless Device-Edge LLM Inference

As large language models (LLMs) move from centralized clouds to mobile edge environments, efficient serving must balance latency, energy consumption, and accuracy under constrained device-edge resources. Query-level routing between lightweight on-device models and stronger edge models provides a flexible mechanism to navigate this trade-off. However, existing routers are designed for centralized cloud settings and optimize token-level costs, failing to capture the dynamic latency and energy overheads in wireless edge deployments. In this paper, we formulate mobile edge LLM routing as a deployment-constrained, cost-aware decision problem, and propose CR^2, a two-stage device-edge routing framework. CR^2 decouples a lightweight on-device margin gate from an edge-side utility selector for deferred queries. The margin gate operates on frozen query embeddings and a user-specified cost weight to predict whether local execution is utility-optimal relative to the best edge alternative under the target operating point. We further introduce a conformal risk control (CRC) calibration procedure that maps each operating point to an acceptance threshold, enabling explicit control of the marginal false-acceptance risk under the full-information utility reference. Experiments on the routing task show that CR^2 closely matches a full-information reference router using only device-side signals before deferral. Compared with strong query-level baselines, CR^2 consistently improves the deployable accuracy-cost Pareto frontier and reduces normalized deployment cost by up to 16.9% at matched accuracy.

Phase-Time Array Enabled Multistatic Sensing with Multi-Level Fusion for UAV Localization

Multistatic collaborative sensing eliminates self-interference, achieves spatial diversity gains, and enables wide-range seamless integrated sensing and communication (ISAC). However, conventional data fusion methods suffer from severe error amplification in geometry-sensitive regions. In addition, the conventional analog phased array solution introduces large beam sweeping overhead, whereas the fully digital arrays request high hardware cost. We propose a multistatic sensing framework enabled by a phase-time array (PTA). The rainbow beamforming maps spatial directions to orthogonal frequency division multiplexing (OFDM) subcarriers, achieving wide-angle coverage with a single radio frequency (RF) chain. We develop two parameter-level schemes-a geometry-aware analytical estimator (GDOP-WLS) and a lightweight multilayer perceptron (PF-MLP)-to mitigate the effects of topological singularities. Additionally, an end-to-end signal-level convolutional neural network (SF-CNN) directly estimates target coordinates from raw signals, avoiding cascaded estimation errors. The results demonstrate that the parameter-level schemes ensure robust convergence under adverse geometric conditions with minimal computational latency. Conversely, the signal-level scheme achieves sub-meter precision but requires an increased computational load. Consequently, the proposed framework establishes a scalable solution for collaborative surveillance of unmanned aerial vehicles (UAVs), providing flexible trade-offs among hardware complexity, latency, and accuracy.

When AI Meets Terahertz: A Survey on the Symbiosis of Artificial Intelligence and Terahertz Networks

The Terahertz (THz) band (0.1-10 THz) has emerged as a critical frontier for future communication systems, offering ultra-wide bandwidths that enable Terabits-per-second (Tbps) wireless links and high-precision sensing and imaging. However, practical deployment of THz systems is hindered by unique challenges, including intricate channel characteristics, high-dimensional and large-scale optimization problems, and highly dynamic network environments. Artificial Intelligence (AI) serves as a transformative enabler to address these challenges, providing robust capabilities for precise modeling, advanced signal processing, complex optimization, real-time decision-making, and prediction, among others. Reciprocally, the unprecedented bandwidth and high-resolution sensing capabilities of THz networks provide a promising physical infrastructure for AI, facilitating training, inference, and data collection. This survey presents a systematic and comprehensive overview of AI-driven solutions across the entire THz communication network and the symbiosis of AI and THz networks. To begin with, a foundational overview of AI technologies tailored for wireless communications is presented. Subsequently, AI-based innovations are investigated, spanning from hardware design, channel modeling, physical layer optimization, up to higher-layer network protocols and advanced THz services, including mobile edge computing and sensing-empowered applications. In parallel, the capacity of THz networks to serve AI is examined, underscoring a profound paradigm shift towards a mutual symbiosis where AI and THz co-evolve and empower each other. Finally, by synthesizing these state-of-the-art advancements and identifying open research directions, this survey highlights the potential of AI in copilot with development of THz communication systems.

WISV: Wireless-Informed Semantic Verification for Distributed Speculative Decoding in Device-Edge LLM Inference

While distributed device-edge speculative decoding enhances resource utilization across heterogeneous nodes, its performance is often bottlenecked by conventional token-level verification strategies. Such rigid alignment leads to excessive rejections, significantly diminishing the accepted sequence length and increasing interaction rounds under fluctuating wireless conditions. In this paper, we propose WISV (Wireless-Informed Semantic Verification), a novel distributed speculative decoding framework that goes beyond strict token-level matching via a channel-aware semantic acceptance policy. WISV integrates a lightweight decision head into the edge-side target LLM to dynamically evaluate speculative tokens by synthesizing high-dimensional hidden representations with instantaneous channel state information (CSI). To optimize the trade-off between verification fidelity and communication overhead, we further design two tailored communication protocols: full-hidden upload and mismatch-first selective-hidden upload. Extensive simulations using a 1B drafter and an 8B target model demonstrate that WISV achieves up to a 60.8% increase in accepted length, a 37.3% reduction in interaction rounds, and a 31.4% improvement in end-to-end latency compared to vanilla speculative decoding across tested settings, while maintaining a negligible task accuracy drop (<1%). Finally, we validate WISV on a hardware testbed comprising an NVIDIA Jetson AGX Orin and an A40-equipped server, confirming its real-world efficacy in accelerating edge-deployed LLM inference.

Towards Semantic-based Agent Communication Networks: Vision, Technologies, and Challenges

The International Telecommunication Union (ITU) identifies "Artificial Intelligence (AI) and Communication" as one of six key usage scenarios for 6G. Agentic AI, characterized by its ca-pabilities in multi-modal environmental sensing, complex task coordination, and continuous self-optimization, is anticipated to drive the evolution toward agent-based communication net-works. Semantic communication (SemCom), in turn, has emerged as a transformative paradigm that offers task-oriented efficiency, enhanced reliability in complex environments, and dynamic adaptation in resource allocation. However, comprehensive reviews that trace their technologi-cal evolution in the contexts of agent communications remain scarce. Addressing this gap, this paper systematically explores the role of semantics in agent communication networks. We first propose a novel architecture for semantic-based agent communication networks, structured into three layers, four entities, and four stages. Three wireless agent network layers define the logical structure and organization of entity interactions: the intention extraction and understanding layer, the semantic encoding and processing layer, and the distributed autonomy and collabora-tion layer. Across these layers, four AI agent entities, namely embodied agents, communication agents, network agents, and application agents, coexist and perform distinct tasks. Furthermore, four operational stages of semantic-enhanced agentic AI systems, namely perception, memory, reasoning, and action, form a cognitive cycle guiding agent behavior. Based on the proposed architecture, we provide a comprehensive review of the state-of-the-art on how semantics en-hance agent communication networks. Finally, we identify key challenges and present potential solutions to offer directional guidance for future research in this emerging field.

Joint Source-Channel-Generation Coding: From Distortion-oriented Reconstruction to Semantic-consistent Generation

Conventional communication systems, including both separation-based coding and AI-driven joint source-channel coding (JSCC), are largely guided by Shannon's rate-distortion theory. However, relying on generic distortion metrics fails to capture complex human visual perception, often resulting in blurred or unrealistic reconstructions. In this paper, we propose Joint Source-Channel-Generation Coding (JSCGC), a novel paradigm that shifts the focus from deterministic reconstruction to probabilistic generation. JSCGC leverages a generative model at the receiver as a generator rather than a conventional decoder to parameterize the data distribution, enabling direct maximization of mutual information under channel constraints while controlling stochastic sampling to produce outputs residing on the authentic data manifold with high fidelity. We further derive a theoretical lower bound on the maximum semantic inconsistency with given transmitted mutual information, elucidating the fundamental limits of communication in controlling the generative process. Extensive experiments on image transmission demonstrate that JSCGC substantially improves perceptual quality and semantic fidelity, significantly outperforming conventional distortion-oriented JSCC methods.

SPOT: Single-Shot Positioning via Trainable Near-Field Rainbow Beamforming

Phase-time arrays, which integrate phase shifters (PSs) and true-time delays (TTDs), have emerged as a cost-effective architecture for generating frequency-dependent rainbow beams in wideband sensing and localization. This paper proposes an end-to-end deep learning-based scheme that simultaneously designs the rainbow beams and estimates user positions. Treating the PS and TTD coefficients as trainable variables allows the network to synthesize task-oriented beams that maximize localization accuracy. A lightweight fully connected module then recovers the user's angle-range coordinates from its feedback of the maximum quantized received power and its corresponding subcarrier index after a single downlink transmission. Compared with existing analytical and learning-based schemes, the proposed method reduces overhead by an order of magnitude and delivers consistently lower two-dimensional positioning error.

MARBLE-Net: Learning to Localize in Multipath Environment with Adaptive Rainbow Beams

Integrated sensing and communication (ISAC) systems demand precise and efficient target localization, a task challenged by rich multipath propagation in complex wireless environments. This paper introduces MARBLE-Net (Multipath-Aware Rainbow Beam Learning Network), a deep learning framework that jointly optimizes the analog beamforming parameters of a frequency-dependent rainbow beam and a neural localization network for high-accuracy position estimation. By treating the phase-shifter (PS) and true-time-delay (TTD) parameters as learnable weights, the system adaptively refines its sensing beam to exploit environment-specific multipath characteristics. A structured multi-stage training strategy is proposed to ensure stable convergence and effective end-to-end optimization. Simulation results show that MARBLE-Net outperforms both a fixed-beam deep learning baseline (RaiNet) and a traditional k-nearest neighbors (k-NN) method, reducing localization error by more than 50\% in a multipath-rich scene. Moreover, the results reveal a nuanced interaction with multipath propagation: while confined uni-directional multipath degrades accuracy, structured and directional multipath can be effectively exploited to achieve performance surpassing even line-of-sight (LoS) conditions.

BitSemCom: A Bit-Level Semantic Communication Framework with Learnable Probabilistic Mapping

Most existing semantic communication systems employ analog modulation, which is incompatible with modern digital communication systems. Although several digital transmission approaches have been proposed to address this issue, an end-to-end bit-level method that is compatible with arbitrary modulation formats, robust to channel noise, and free from quantization errors remains lacking. To this end, we propose BitSemCom, a novel bit-level semantic communication framework that realizes true joint source-channel coding (JSCC) at the bit level. Specifically, we introduce a modular learnable bit mapper that establishes a probabilistic mapping between continuous semantic features and discrete bits, utilizing the Gumbel-Softmax trick to enable differentiable bit generation. Simulation results on image transmission demonstrate that BitSemCom achieves both competitive performance and superior robustness compared to traditional separate source-channel coding (SSCC) schemes, and outperforms deep learning based JSCC with uniform 1-bit quantization, validating the effectiveness of the learnable bit mapper. Despite these improvements, the bit mapper adds only 0.42% parameters and 0.09% computational complexity, making BitSemCom a lightweight and practical solution for real-world semantic communication.

Spatial Computing Communications for Multi-User Virtual Reality in Distributed Mobile Edge Computing Network

Immersive virtual reality (VR) applications impose stringent requirements on latency, energy efficiency, and computational resources, particularly in multi-user interactive scenarios. To address these challenges, we introduce the concept of spatial computing communications (SCC), a framework designed to meet the latency and energy demands of multi-user VR over distributed mobile edge computing (MEC) networks. SCC jointly represents the physical space, defined by users and base stations, and the virtual space, representing shared immersive environments, using a probabilistic model of user dynamics and resource requirements. The resource deployment task is then formulated as a multi-objective combinatorial optimization (MOCO) problem that simultaneously minimizes system latency and energy consumption across distributed MEC resources. To solve this problem, we propose MO-CMPO, a multi-objective consistency model with policy optimization that integrates supervised learning and reinforcement learning (RL) fine-tuning guided by preference weights. Leveraging a sparse graph neural network (GNN), MO-CMPO efficiently generates Pareto-optimal solutions. Simulations with real-world New Radio base station datasets demonstrate that MO-CMPO achieves superior hypervolume performance and significantly lower inference latency than baseline methods. Furthermore, the analysis reveals practical deployment patterns: latency-oriented solutions favor local MEC execution to reduce transmission delay, while energy-oriented solutions minimize redundant placements to save energy.