Searcharxiv⌕ Search

arXiv subjects

Kezhi Wang

Publications and source records attributed to Kezhi Wang.

At least 19 recordsLinked to original sources

Multi-LLM Agentic AI at the Edge: Joint Agent Scheduling and Resource Allocation

In this paper, an edge-enabled multi-large language model (LLM) agentic AI architecture is proposed, where one supervisor AI agent and multiple worker AI agents cooperatively execute users' requests at the edge. The supervisor AI agent decouples the user request into a series of sub-tasks and dynamically dispatches them to LLM-equipped worker AI agents via two agentic workflows, i.e., parallel and serial workflows, with a two-level retry mechanism to enhance execution reliability. To prolong the service duration of worker AI agents, the energy minimization problems are formulated by jointly considering AI agent selection and resource allocation, subject to task execution latency and quality of service (QoS) constraints. A resource allocation scheme based on alternating optimization (AO) is proposed. Specifically, for the parallel workflow, the scheme decouples the original problem into bandwidth allocation, retrieval selection and AI agent selection sub-problems, which are iteratively solved by the proposed successive convex approximation (SCA), Lagrangian relaxation (LR), and Gale-Shapley (GS) or LLM-based algorithms, respectively. For the serial workflow, the problem is similarly decoupled into service time allocation, retrieval selection and AI agent selection sub-problems; the optimal service time allocation is obtained via Karush-Kuhn-Tucker (KKT) conditions, while the latter two sub-problems are addressed by extending the proposed algorithms to the serial scenario. Simulation results show that the proposed resource allocation scheme can reduce system energy consumption compared with other benchmarks, while experiments on a multi-LLM agentic AI system based on Qwen and Llama demonstrate improved task execution success rates.

cs.AI↗

Agentic AI Empowered Intent-Based Networking for 6G

The transition towards sixth-generation (6G) wireless networks necessitates autonomous orchestration mechanisms capable of translating high-level operational intents into executable network configurations. Existing approaches to Intent-Based Networking (IBN) rely upon either rule-based systems that struggle with linguistic variation or end-to-end neural models that lack interpretability and fail to enforce operational constraints. This paper presents a hierarchical multi-agent framework where Large Language Model (LLM) based agents autonomously decompose natural language intents, consult domain-specific specialists, and synthesise technically feasible network slice configurations through iterative reasoning-acting (ReAct) cycles. The proposed architecture employs an orchestrator agent coordinating two specialist agents, namely Radio Access Network (RAN) and Core Network agents, via ReAct-style reasoning, grounded in structured network state representations. Experimental evaluation across diverse benchmark scenarios demonstrates that the proposed system outperforms monolithic agents, rule-based systems, and direct LLM prompting, with architectural principles applicable to Open RAN (O-RAN) deployments. The results also demonstrate that whilst contemporary LLMs possess substantial general telecommunications knowledge, structured prompt engineering encoding domain-specific decision thresholds and operational policies is essential for reliable network automation performance.

cs.AI↗

Can We Trust AI in 6G? Verifiable and Auditable AI-Driven Trustworthy Wireless Networks

Mobile network operators are increasingly exploring the use of artificial intelligence (AI) to automate network tasks such as cell selection and mobility management. Current assurance methods for these AI functions are forms of output testing. They check what a function decides, but they cannot show why it decided that way, and two functions can pass the same tests for different reasons. In this paper, we propose mechanistic auditing, which inspects the internal features of an AI function and checks them against machine-verifiable 3GPP specifications. We set out a three-step auditing principle that locates protocol-relevant features, verifies whether decisions depend on them, and audits each decision against them. We then present an audit-native network architecture. In this architecture, a dedicated verification agent certifies each AI function before deployment and audits its decisions during operation. In a case study on a language model for LTE signalling, we find internal features that carry the 3GPP handover concepts. Removing them lowers the model's accuracy on handover tasks from 96% to 0%, while removing the same number of random features changes its accuracy by less than two points. An audit of a handover decision can therefore check whether these features are active when the model makes that decision. We also discuss the open challenges that remain before mechanistic auditing can enter telecommunications practice and standardisation.

cs.NI↗

Mechanistic Insights into LoRA: Layer Sparsity for Adaptive Fine-Tuning via Path Patching

Low-Rank Adaptation (LoRA) has emerged as the dominant paradigm for parameter-efficient fine-tuning of large language models. Standard all-layer LoRA applies adaptation throughout the transformer, despite heterogeneous contributions from its components. In this work, we conduct a systematic mechanistic interpretability analysis to understand how LoRA affects model internals. We observe that LoRA's adaptation effect is highly non-uniform, with significant component-wise and layer-wise sparsity. Most critically, we find that important layers are highly task-dependent, with limited overlap across tasks. Motivated by these insights, we propose Adaptive-LoRA, a calibration-driven method that automatically identifies task-specific layers via frozen-base zero-ablation, enabling efficient layer selection without exhaustive search. Extensive experiments on Qwen2.5-1.5B across 11 diverse reasoning tasks demonstrate that Adaptive-LoRA outperforms full-layer LoRA while using only 30% of layers, achieving a $3.5\times$ reduction in adapter parameters. This work bridges mechanistic interpretability and practical efficiency, providing both fundamental insights and a principled approach for adaptive fine-tuning.

cs.LG↗

Smart-TCP: An Agentic AI-based Autonomous and Adaptive TCP Protocol

The Transmission Control Protocol (TCP) relies on deterministic state machines and sequence-number arithmetic to ensure reliable communication. However, hard-coded protocol logic is difficult to adapt to increasingly complex and dynamic network conditions. This paper proposes Smart-TCP, an agentic AI-based transport protocol framework that organizes TCP control logic as a fast/slow model-assisted decision process. Specifically, a feature-aware classifier routes routine segments to a lightweight Small Language Model (SLM) fast path and anomalous or boundary cases to a Large Language Model (LLM) slow path, while an Arithmetic Logic Unit (ALU) handles deterministic computation of sequence and acknowledgment numbers. A state module maintains connection state, packet history, and key control variables, enabling protocol decisions over the full session context. A scoped Protocol Guard checks candidate decisions against RFC-derived rules before execution. We evaluate Smart-TCP through path classification, atomic packet processing, slow-path anomaly response, and end-to-end session interaction. Experimental results show that Smart-TCP achieves 99.14% action accuracy on 700 slow-path anomaly and fallback samples, and a 100% full-lifecycle success rate over 300 ideal fast-path end-to-end session windows. The ordinary 32-KiB transfer tests achieve a 96.5% completion rate at 20% segment loss. These results suggest that separating model-based protocol decisions from deterministic arithmetic improves the reliability of TCP control for network service operation.

cs.NI↗

FlashSAM: Lightweight Vision Model for Multi-UAV Token Communication in Low-Latitude Wireless Networks

Token Communication (TokenCom) is a promising paradigm for low-altitude wireless networks, as it focuses on transmitting task-relevant core information, particularly in environments with uncertainty, noise, and stringent bandwidth constraints. However, existing TokenCom systems still face several challenges, including inefficient knowledge base construction, ineffective token encoding, and limited support for multi-user token sharing. To address these issues, we propose a Lightweight Vision Model-based Multi-Unmanned Aerial Vehicle (UAV) Token Communication (LVM-MTC) system. First, we develop a lightweight Segment Anything Model (SAM), termed FlashSAM, which incorporates a set of lightweight convolutional modules to significantly reduce the number of model parameters. Building on FlashSAM, we construct a Lightweight Knowledge Base (LKB) to enable efficient object-level perception. Next, we design an Efficient Token Codec (ETC) based on the Masked Autoencoder (MAE) architecture. ETC improves compression efficiency at both the pixel and token levels, and provides lightweight token decoding tailored for resource-constrained UAVs. Furthermore, we propose a Multi-UAV Token Sharing (MTS) scheme for multi-UAV TokenCom. By measuring token similarity across UAVs, MTS consolidates similar tokens and transmits them through broadcast transmission, thereby further improving transmission efficiency. Finally, simulation results validate the feasibility and effectiveness of the proposed LVM-MTC system.

cs.IT↗

Active Movable-Element RIS Assisted Vehicular Semantic Communications: Modeling and Optimization

Severe signal blockage and fast-varying channels in vehicular environments pose critical challenges to reliable semantic communication. To address these, this paper proposes a novel Row-Movable Active Reconfigurable Intelligent Surface (RM-A-RIS) assisted vehicular semantic communication system. This architecture uniquely combines active signal amplification with element mobility to compensate for multiplicative fading and reconstruct channel geometry, thereby enhancing spatial diversity. We formulate a joint optimization problem to maximize Semantic Spectral Efficiency (SSE) by coordinating RIS element positions, active reflection coefficients, and semantic symbol length. An efficient Alternating Optimization (AO) algorithm is developed to tackle the coupled non-convexity. Simulation results demonstrate that the proposed scheme substantially outperforms existing benchmarks, achieving up to 132.9%, 9.2%, and 35.2% improvements in Sum-Semantic Spectral Efficiency (Sum-SSE) compared to the passive RIS, fixed-position active RIS, and QPSO baselines, respectively.

cs.NI↗

From Traditional Automation to Embodied Wireless Intelligence: Vision-Language-Action Empowered Physics-Aware Communication Networks

Wireless network automation has progressed from rule-based self-organising networks (SON) to data-driven optimisation, yet existing systems remain fundamentally disembodied. They act on performance indicators without perceiving the physical environment that governs radio propagation. We propose the embodied intelligent empowered base station (eBS), a paradigm that adopts a Vision-Language-Action (VLA) pipeline to transform base stations into autonomous AI agents capable of situated perception, causal physical reasoning, and physics-aware action generation. The eBS employs a two-tier asynchronous architecture: a Semantic Planner powered by a frontier Vision-Language Model (VLM) generates structured action directives on human timescales, whilst a Tactical Controller executes real-time adaptation. Case studies demonstrate that a single VLA pipeline, without task-specific training, can perform zero-shot material reasoning, generalise across viewpoints, and predict dynamic events before signal degradation occurs. These results illustrate a paradigm shift from traditional rule-following network automation to embodied-intelligence-empowered future wireless networks.

cs.NI↗

Cell-Level Channel Shaping for Rydberg Atomic Quantum Receivers in Satellite Uplinks With Doppler-Enabled Superheterodyne Reception

In this paper, we propose a self-superheterodyne Rydberg uniform array receiver for satellite uplink communications, in which the Doppler shift naturally induced by satellite motion is exploited to generate the intermediate-frequency signal. We first develop a near-field local oscillator (LO) synthesis model and characterize the spatially varying LO electric field across the Rydberg vapor cells. Based on a vapor-cell-center approximation, a closed-form radio frequency (RF)-to-optical conversion is derived, establishing an explicit bridge between the incident satellite signal and the LO-induced cell-level response. The derived model reveals that the programmable LO serves as an analog-domain channel-shaping mechanism by controlling the cell-level transduction gain, phase response, and phase-matching behavior. Building upon this equivalent channel model, we formulate an LO design problem that maximizes the Shannon capacity of the effective channel, and develop an efficient optimization algorithm for the LO amplitudes and phases. Simulation results demonstrate that the vapor-cell transduction can reshape the effective channel, adjust the beam-pattern alignment, and moderately reduce the inter-user correlation under suitable LO configurations. Furthermore, the proposed LO design significantly improves the achievable capacity over benchmark schemes, offering a promising self-superheterodyne Rydberg architecture for future satellite communication systems.

eess.SP↗

SLM, LLM or Agentic AI? Toward Intelligent UAV-Enabled WPT Systems in Low-Altitude Economy Networks

Unmanned Aerial Vehicles (UAVs) have become key enabling platforms for low-altitude economic networks, yet achieving efficient and adaptive optimization under resource-constrained and dynamic environments remains challenging. This paper investigates language models for UAV-enabled Wireless Power Transfer (WPT) systems. First, a lightweight Small Language Model (SLM)-based solution is developed using a pre-trained BERT backbone, enhanced UAV embeddings and contextual features, a geometry-aware path decoder, and ensemble inference to achieve low complexity, low latency, and high energy efficiency. Second, an Agentic AI-based framework is designed to exploit the reasoning and interactive capabilities of Large Language Models (LLMs). It integrates four collaborative agents-Initializer, Actor, Critic, and Reflector-to form a closed loop of generation, optimization, evaluation, and reflection for iterative UAV path and energy optimization. Finally, simulations compare the SLM-, LLM-, and Agentic AI-based approaches.

cs.IT↗

Explainable Task-Oriented Token Communication for AI-Native 6G Networks

The integration of Foundation Models (FMs) and wireless communications is driving the evolution of image communication from bit-accurate transmission toward task-oriented transmission. However, existing task-oriented image communication methods still face three major challenges: insufficient task-oriented Token representation, inadequate collaboration between Visual Tokens and Task Tokens, and limited interpretability of task decisions. To address these challenges, we propose an Explainable Task-Oriented Token Communication (ET-TokenCom) framework. By treating Tokens as unified units for information representation and transmission, the proposed framework constructs an end-to-end communication link that spans visual perception, wireless transmission, and task reasoning. At the transmitter, the ET-TokenCom framework extracts Visual Tokens from images to preserve low-level visual information. Meanwhile, Task Tokens generated by the FM are introduced to represent the target information and decision intent required by the current task. A Cross-Modal Attention (CMA) fusion mechanism is further designed, enabling Task Tokens to explicitly guide the selection, weighting, and transmission of Visual Tokens. At the receiver, the framework integrates Token decoding with an explainable output mechanism, where attention heatmaps are generated to highlight critical perceptual regions under different task objectives and reveal the influence of Task Tokens on the outputs. Finally, simulation results validate the effectiveness and robustness of the proposed ET-TokenCom framework.

eess.IV↗

Revolutionizing Wireless Communications with Space Data Centers: Applications and Open Challenges

Space data centers (SDCs) are emerging as a promising orbital computing infrastructure for the future AI industry. Unlike conventional satellites that mainly serve as relay nodes or lightweight onboard processors, SDCs integrate communication, computing, storage, and control capabilities in orbit, enabling persistent service support for data-intensive and intelligence-driven space applications. In this article, we investigate how SDCs may transform space communication paradigms from connectivity-oriented data transmission toward task-oriented and service-centric information exchange. We first present a hierarchical SDC network architecture consisting of access, relay, computing, and control layers, and outline possible deployment strategies. We then explore representative future application scenarios enabled by SDCs, highlighting their communication characteristics and associated research challenges. Simulation results further demonstrate the effectiveness of SDCs in reducing control-layer latency in hierarchical space networks. Finally, we identify key research directions toward the practical deployment of SDCs.

cs.NI↗

Vision-Language-Action Models Meet World Models: Embodied Agentic AI for Low-Altitude Wireless Networks

Low-Altitude Wireless Networks (LAWNs), composed of Unmanned Aerial Vehicles (UAVs) and other aerial platforms, provide integrated perception, communication, and computation services in low-altitude airspace. However, deploying large generative models in this domain faces three major challenges: 1) Limited embodied action mapping; 2) Inadequate physical environment modeling; 3) Insufficient closed-loop optimization. To address these challenges, this study proposes an Embodied Agentic UAV framework. Centered on a Vision-Language-Action (VLA) model as the execution core, the framework establishes an end-to-end embodied decision-making pipeline from multimodal environmental perception to continuous control generation. In addition, a World Model (WM) is introduced to capture the coupling between UAV actions and environmental state evolution, thereby supporting environment prediction, policy verification, and dynamic optimization. Furthermore, memory and reflection mechanisms are incorporated to form an adaptive closed-loop optimization paradigm of decision, execution, evaluation, and update, thereby enhancing the system's autonomous decision-making capability and continual evolution ability in complex dynamic environments. Experimental results validate its effectiveness in enabling robust, predictive, and sustainable autonomous control in LAWNs.

cs.IT↗

Beyond the RF Paradigm: Rydberg Atomic Receivers for Next-Generation IoT

Next-generation Internet-of-Things (IoT) is evolving toward a ubiquitous, ultra-low-power, and multi-band heterogeneous networking paradigm that seamlessly integrates terrestrial, non-terrestrial, and ambient devices. This vision places unprecedented demands on conventional radio frequency (RF) receivers, whose fundamental bottlenecks in sensitivity, power consumption, coverage, and multi-band operation are rooted in the RF antenna. To tackle these issues, we show that the quantum properties of Rydberg atomic quantum receivers (RAQRs), including ultra-high sensitivity, broad frequency agility, and diverse reception modalities, provide a physically distinct receiver-side path that replaces the conventional antenna-and-low-noise-amplifier chain. Using LoRa, narrowband IoT, and ambient IoT as case studies, this article shows that RAQRs deliver significant gains in weak-uplink, low-power, and battery-free regimes. A stochastic-geometry analysis in cellular and cell-free architectures then maps these device-level gains onto network coverage, where the RAQR retains roughly a 4 dB half-coverage advantage over the RF receiver in sparse deployments at \(λ\sim 10^{-5}~{\mathrm m}^{-2}\), with the gain eroded as device density grows. The open challenges are presented to stand between current RAQR prototypes and deployable IoT infrastructure.

eess.SP↗

TWIST: Closed-Loop token Synchronization for Application-Aware Wireless Digital Twins

Wireless digital twins require repeated synchronization between a time-evolving physical scene and its digital counterpart under limited and time-varying communication resources. For perception-centric twins, pixel-domain transmission or uniformly protected bitstreams can be mismatched to the semantic state consumed by twin-side applications. This paper proposes TWIST, a closed-loop token synchronization framework for application-aware wireless digital twins. TWIST represents each physical observation as a token and synchronizes this state over a wireless link, rather than optimizing visual reconstruction. Token positions are grouped by task relevance and protected through mode-conditioned unequal error protection under low-, medium-, and high-synchronization modes. At the twin side, decoding confidence converts unreliable hard token decisions into erasures, which are restored by a completion model before updating the semantic twin state. The recovered state supports traffic-state inference and generates compact feedback statistics, including channel quality, receiver uncertainty, semantic drift, and application priority, for subsequent mode adaptation. Experiments on a dynamic road-scene digital-twin scenario show that TWIST improves traffic-state inference and semantic twin-state synchronization compared with fixed-mode and channel-only adaptation strategies, while reducing the average synchronization cost relative to always-high transmission.

eess.IV↗

TONIC: Token-Centric Semantic Communication for Task-Oriented Wireless Systems

Tokens are becoming the basic units through which foundation models represent and process information for understanding and inference. However, traditional wireless communication, centered on bit-level fidelity, faces a mismatch between what is transmitted reliably and what downstream models actually consume. This mismatch calls for a communication design that directly accounts for token-level task relevance and downstream model requirements, rather than treating all transmitted bits as equally important. In this paper, we propose TONIC, a token-centric semantic communication framework for task-oriented wireless systems. The transmitter converts each source sample into a sequence of tokens, estimates token-level task relevance, and allocates protection through utility-aware unequal error protection under a fixed channel-use budget. At the receiver, token-level confidence is used to gate unreliable decisions, turning harmful substitutions into recoverable erasures before a Transformer-based completion model restores the masked tokens for final task inference. Our framework combines transmitter-side semantic-aware protection with receiver-side confidence-aware gating in a modular and interpretable architecture, rather than relying solely on fully black-box end-to-end learning. We further establish a utility-aware Bayes-risk interpretation for the receiver-side gating rule and study its interaction with unequal protection and completion. Experimental results on image classification show that TONIC consistently outperforms separation-based schemes, the pixel-domain DeepJSCC baseline, and token-domain baselines under matched communication budgets over AWGN, Rayleigh, and Rician channels.

cs.LG↗

Toward Communication-Efficient Space Data Centers: Bottlenecks, Architectures, and New Paradigms

The rapid growth of foundation model training and large-scale AI services has driven ground data centers toward unprecedented power densities, intensifying challenges in energy supply, cooling, and spatial scalability. Space Data Centers (SDCs) have emerged as a promising paradigm for hosting energy-intensive computing infrastructures in orbit, leveraging continuous solar energy and radiative cooling advantages. However, unlike ground facilities primarily constrained by power and site availability, SDCs are fundamentally limited by communication capability. The gap between petabit-scale internal data exchange in ground data centers and the gigabit-scale capacity of ground-space links forms a critical bottleneck. This article systematically analyzes communication constraints in SDC architectures and explores semantic communication as a key enabling paradigm. By transmitting compact, task-relevant semantic representations instead of raw data, uplink pressure can be substantially reduced. The feasibility of communication-efficient orbital AI infrastructures is demonstrated through the evaluation of a multi-layer heterogeneous SDC framework consisting of relay satellites and orbital computing nodes operating under coupled energy and thermal constraints. The article further outlines open research challenges toward scalable deployment.

cs.NI↗

Single-Step Six-Dimensional Movable Antenna Reconfiguration for High-Mobility IoV: Modeling, Analysis, and Optimization

The Six-Dimensional Movable Antenna (6DMA) system has emerged as a promising technology to enhance wireless capacity by fully exploiting spatial degrees of freedom. However, applying 6DMA to high-mobility Internet of Vehicles (IoV) scenarios faces significant challenges, primarily due to the difficulty of acquiring instantaneous Channel State Information (CSI) and the risk of service interruptions caused by mechanical reconfiguration delays. To address these issues, this paper proposes a low-complexity, CSI-free single-step reconfiguration framework. First, we design a deterministic discrete position generation scheme based on a latitude-longitude grid with inherent topological structures. Leveraging graph theory, we explicitly model and theoretically derive the lower bounds of movement and time costs for antenna reconfiguration. Subsequently, utilizing the directional sparsity of 6DMA channels, we develop an adaptive optimization strategy that fuses offline environmental priors with online historical feedback. Furthermore, a periodic reconfiguration mechanism based on predicted cumulative vehicle distributions is introduced. By strictly restricting antenna adjustments to the first-order spatial neighborhood, the proposed single-step method effectively eliminates service interruptions. Simulation results demonstrate that the proposed scheme significantly outperforms traditional fixed and global-search-based benchmarks in terms of uplink sum rate, while incurring negligible mechanical overhead and latency, thereby validating its feasibility and robustness in highly dynamic vehicular networks.

cs.NI↗