arXiv subjects

Shiwen Mao

Publications and source records attributed to Shiwen Mao.

At least 19 recordsLinked to original sources

arXiv2026

Rethinking Wireless Communications through Formal Mathematical AI Reasoning

Mathematical analysis has long underpinned wireless communication theory, yet the growing complexity of next-generation systems demands increasingly sophisticated reasoning from domain experts. Recent advances in AI mathematical reasoning, from formal theorem proving to large language model (LLM)-based derivation, offer a promising but largely unexplored path forward. Here we argue that wireless communications is a uniquely structured domain for formal AI reasoning, and propose a three-layer framework of verification, derivation, and discovery to rethink how wireless mathematical knowledge is established.

eess.SP↗

arXiv2026

Application-Aware Twin-in-the-Loop Planning for Federated Split Learning over Wireless Edge Networks

We investigate task-success-oriented resource allocation for federated split learning (FSL) at the wireless edge. In this setting, the server must jointly determine bandwidth, transmit power, split-layer placement, compression level, and terminal participation under per-round deadline, memory, and spectrum constraints. These coupled decisions affect wireless transmission, model training, and task execution, which evolve at different time scales and cannot be efficiently evaluated through repeated real-world trials. To address this challenge, we propose TiLP, a twin-in-the-loop planner that evaluates candidate decisions through a cross-domain digital twin before execution. The twin integrates network, training, and task sub-twins, with each sub-twin calibrated at the time scale of the process it models. Based on this twin, TiLP performs receding-horizon cross-entropy method planning with actor-critic guidance to search over mixed continuous-discrete decisions. Experiments on LIBERO robotic manipulation tasks over a Sionna RT-simulated wireless network show that TiLP improves task success by 9.5 percentage points over the strongest single-axis baseline, while satisfying the per-round deadline and energy budget.

cs.NI↗

arXiv2026

A Geometric Algebra-informed NeRF Framework for Generalizable Wireless Channel Prediction

In this paper, we propose the geometric algebra-informed neural radiance fields (GAI-NeRF), a novel framework for wireless channel prediction that leverages geometric algebra attention mechanisms to capture ray-object interactions in complex propagation environments. Our approach incorporates global token representations, drawing inspiration from transformer architectures in language and vision domains, to aggregate learned spatial-electromagnetic features and enhance scene understanding. We identify limitations in conventional static ray tracing modules that hinder model generalization and address this challenge through a new ray tracing architecture. This design enables effective generalization across diverse wireless scenarios while maintaining computational efficiency. Experimental results demonstrate that GAI-NeRF achieves superior performance in channel prediction tasks by combining geometric algebra principles with neural scene representations, offering a promising direction for next-generation wireless communication systems. Moreover, GAI-NeRF greatly outperforms existing methods across multiple wireless scenarios. To ensure comprehensive assessment, we further evaluate our approach against multiple benchmarks using newly collected real-world indoor datasets tailored for single-scene downstream tasks and generalization testing, confirming its robust performance in unseen environments and establishing its high efficacy for wireless channel prediction.

cs.NI↗

arXiv2026

Semantic Communication with an LLM-enabled Knowledge Base

Semantic communication (SC) can achieve superior coding and transmission performance based on the knowledge contained in the semantic knowledge base (KB). However, conventional KBs consist of source KBs and channel KBs, which are often costly to obtain data and limited in data scale. Fortunately, large language models (LLMs) have recently emerged with extensive knowledge and generative capabilities. Therefore, this paper proposes an SC system with LLM-enabled knowledge base (SC-LMKB), which utilizes the generation ability of LLMs to significantly enrich the KB of SC systems. In particular, we first design an LLM-enabled generation mechanism with a prompt engineering strategy for source data generation (SDG) and a cross-attention alignment method for channel data generation (CDG). However, hallucinations from LLMs may cause semantic noise, thus degrading SC performance. To mitigate the hallucination issue, a cross-domain fusion codec (CDFC) framework with a hallucination filtering phase and a cross-domain fusion phase is then proposed for SDG. In particular, the first phase filters out new data generated by the LMKB irrelevant to the original data based on semantic similarity. Then, a cross-domain fusion phase is proposed, which fuses source data with LLM-generated data based on their semantic importance, thereby enhancing task performance. Besides, a joint training objective that combines cross-entropy loss and reconstruction loss is proposed to reduce the impact of hallucination on CDG. Experiment results on three cross-modality retrieval tasks demonstrate that the proposed SC-LMKB can achieve up to 72.6\% and 90.7\% performance gains compared to conventional SC systems and LLM-enabled SC systems, respectively.

eess.SP↗

arXiv2026

Compact LLM Deployment and World Model Assisted Offloading in Mobile Edge Computing

This paper investigates compact large language model (LLM) deployment and world-model-assisted inference offloading in mobile edge computing (MEC) networks. We first propose an edge compact LLM deployment (ECLD) framework that jointly applies structured pruning, low-bit quantization, and knowledge distillation to construct edge-deployable LLM variants, and we evaluate these models using four complementary metrics: accessibility, energy consumption, hallucination rate, and generalization accuracy. Building on the resulting compact models, we formulate an MEC offloading optimization problem that minimizes the long-term average inference latency subject to per-device energy budgets and LLM-specific quality-of-service constraints on effective accuracy and hallucination. To solve this problem under unknown and time-varying network dynamics, we develop a world model-proximal policy optimization (PPO) algorithm, which augments an on-policy PPO algorithm with a learned recurrent world model that provides improved value targets and short imagination rollouts. Extensive experiments on Llama-3.1-8B, Qwen3-8B, and Mistral-12B show that ECLD compresses base models by about 70-80% in storage (i.e., from 15.3 GB to 3.3 GB for Llama-3.1-8B) and reduces per-query energy consumption by up to 50%, while largely preserving accuracy and often lowering hallucination compared with quantization-only or pruning-only baselines. Moreover, they also show that world model-PPO speeds up convergence by about 50%, improves the final reward by 15.8% over vanilla PPO, and reduces average inference latency by 12-30% across different user populations, while satisfying the accuracy and hallucination constraints and approaching the generation quality of always-offloading with much of the efficiency of local execution.

cs.NI↗

arXiv2026

Low-Complexity Distributed Combining Design for Near-Field Cell-Free XL-MIMO Systems

In this paper, we investigate the low-complexity distributed combining scheme design for near-field cell-free extremely large-scale multiple-input-multiple-output (CF XL-MIMO) systems. Firstly, we construct the uplink spectral efficiency (SE) performance analysis framework for CF XL-MIMO systems over centralized and distributed processing schemes. Notably, we derive the centralized minimum mean-square error (CMMSE) and local minimum mean-square error (LMMSE) combining schemes over arbitrary channel estimators. Then, focusing on the CMMSE and LMMSE combining schemes, we propose five low-complexity distributed combining schemes based on the matrix approximation methodology or the symmetric successive over relaxation (SSOR) algorithm. More specifically, we propose two matrix approximation methodology-aided combining schemes: Global Statistics \& Local Instantaneous information-based MMSE (GSLI-MMSE) and Statistics matrix Inversion-based LMMSE (SI-LMMSE). These two schemes are derived by approximating the global instantaneous information in the CMMSE combining and the local instantaneous information in the LMMSE combining with the global and local statistics information by asymptotic analysis and matrix expectation approximation, respectively. Moreover, by applying the low-complexity SSOR algorithm to iteratively solve the matrix inversion in the LMMSE combining, we derive three distributed SSOR-based LMMSE combining schemes, distinguished from the applied information and initial values.

eess.SP↗

arXiv2026

Large Multimodal Models for Embodied Intelligent Driving: The Next Frontier in Self-Driving?

The advent of Large Multimodal Models (LMMs) offers a promising technology to tackle the limitations of modular design in autonomous driving, which often falters in open-world scenarios requiring sustained environmental understanding and logical reasoning. Besides, embodied artificial intelligence facilitates policy optimization through closed-loop interactions to achieve the continuous learning capability, thereby advancing autonomous driving toward embodied intelligent (El) driving. However, such capability will be constrained by relying solely on LMMs to enhance EI driving without joint decision-making. This article introduces a novel semantics and policy dual-driven hybrid decision framework to tackle this challenge, ensuring continuous learning and joint decision. The framework merges LMMs for semantic understanding and cognitive representation, and deep reinforcement learning (DRL) for real-time policy optimization. We start by introducing the foundational principles of EI driving and LMMs. Moreover, we examine the emerging opportunities this framework enables, encompassing potential benefits and representative use cases. A case study is conducted experimentally to validate the performance superiority of our framework in completing lane-change planning task. Finally, several future research directions to empower EI driving are identified to guide subsequent work.

cs.RO↗

arXiv2026

Low-Altitude Satellite-AAV Collaborative Joint Mobile Edge Computing and Data Collection via Diffusion-based Deep Reinforcement Learning

The integration of satellite and autonomous aerial vehicle (AAV) communications has become essential for the scenarios requiring both wide coverage and rapid deployment, particularly in remote or disaster-stricken areas where the terrestrial infrastructure is unavailable. Furthermore, emerging applications increasingly demand simultaneous mobile edge computing (MEC) and data collection (DC) capabilities within the same aerial network. However, jointly optimizing these operations in heterogeneous satellite-AAV systems presents significant challenges due to limited on-board resources and competing demands under dynamic channel conditions. In this work, we investigate a satellite-AAV-enabled joint MEC-DC system where these platforms collaborate to serve ground devices (GDs). Specifically, we formulate a joint optimization problem to minimize the average MEC end-to-end delay and AAV energy consumption while maximizing the collected data. Since the formulated optimization problem is a non-convex mixed-integer nonlinear programming (MINLP) problem, we propose a Q-weighted variational policy optimization-based joint AAV movement control, GD association, offloading decision, and bandwidth allocation (QAGOB) approach. Specifically, we reformulate the optimization problem as an action space-transformed Markov decision process to adapt the variable action dimensions and hybrid action space. Subsequently, QAGOB leverages the multi-modal generation capacities of diffusion models to optimize policies and can achieve better sample efficiency while controlling the diffusion costs during training. Simulation results show that QAGOB outperforms five other benchmarks, including traditional DRL and diffusion-based DRL algorithms. Furthermore, the MEC-DC joint optimization achieves significant advantages when compared to the separate optimization of MEC and DC.

cs.NI↗

arXiv2026

Toward Resource-Efficient Collaboration of Large AI Models in Mobile Edge Networks

The collaboration of large artificial intelligence (AI) models in mobile edge networks has emerged as a promising paradigm to meet the growing demand for intelligent services at the network edge. By enabling multiple devices to cooperatively execute submodels or subtasks, collaborative AI enhances inference efficiency and service quality with constrained resources. However, deploying large AI models in such environments remains challenging due to the intrinsic mismatch between model complexity and the limited computation, memory, and communication resources in edge networks. This article provides a comprehensive overview of the system architecture for collaborative AI in mobile edge networks, along with representative application scenarios in transportation and healthcare. We further present recent advances in resource-efficient collaboration techniques, categorized into spatial and temporal approaches. The major spatial approaches include federated tuning, mixture of experts, patch-based diffusion, and hierarchical diffusion. Meanwhile, the important temporal approaches encompass split learning, cascading inference, speculative decoding, and routing inference. Building upon these foundations, we propose a multi-stage diffusion framework that enables elastic distribution of large generative models across heterogeneous edge resources. Experimental results demonstrate that our framework achieves performance improvement in both efficiency and adaptability for data generation.

cs.NI↗

arXiv2025

Hierarchical Online Optimization Approach for IRS-enabled Low-altitude MEC in Vehicular Networks

In this paper, we propose an intelligent reflecting surface (IRS)-enabled low-altitude multi-access edge computing (MEC) architecture, where an aerial MEC server cooperates with a terrestrial MEC server to provide computing services, while hybrid IRSs (i.e., building-installed and UAV-carried IRSs) are deployed to enhance the air-ground connectivity under blockage. Based on this architecture, we formulate a multi-objective optimization problem (MOOP) to minimize the task completion delay and energy consumption by jointly optimizing task offloading, UAV trajectory control, IRS phase-shift configuration, and computation resource allocation. The considered problem is NP-hard, and thus we propose a hierarchical online optimization approach (HOOA) to efficiently solve the problem. Specifically, we reformulate the MOOP as a Stackelberg game, where MEC servers collectively act as the leader to determine the system-level decisions, while the vehicles act as followers to make individual decisions. At the follower level, we present a many-to-one matching mechanism to generate feasible discrete decisions. At the leader level, we propose a generative diffusion model-enhanced twin delayed deep deterministic policy gradient (GDMTD3) algorithm integrated with a Karush-Kuhn-Tucker (KKT)-based method, which is a deep reinforcement learning (DRL)-based approach, to determine the continuous decisions. Simulation results demonstrate that the proposed HOOA achieves significant improvements, which reduces average task completion delay by 2.5% and average energy consumption by 3.1% compared with the best-performing benchmark approach and state-of-the-art DRL algorithm, respectively. Moreover, the proposed HOOA exhibits superior convergence stability while maintaining strong robustness and scalability in dynamic environments.

cs.NI↗

arXiv2025

Encrypted Traffic Detection in Resource Constrained IoT Networks: A Diffusion Model and LLM Integrated Framework

The proliferation of Internet-of-things (IoT) infrastructures and the widespread adoption of traffic encryption present significant challenges, particularly in environments characterized by dynamic traffic patterns, constrained computational capabilities, and strict latency constraints. In this paper, we propose DMLITE, a diffusion model and large language model (LLM) integrated traffic embedding framework for network traffic detection within resource-limited IoT environments. The DMLITE overcomes these challenges through a tri-phase architecture including traffic visual preprocessing, diffusion-based multi-level feature extraction, and LLM-guided feature optimization. Specifically, the framework utilizes self-supervised diffusion models to capture both fine-grained and abstract patterns in encrypted traffic through multi-level feature fusion and contrastive learning with representative sample selection, thus enabling rapid adaptation to new traffic patterns with minimal labeled data. Furthermore, DMLITE incorporates LLMs to dynamically adjust particle swarm optimization parameters for intelligent feature selection by implementing a dual objective function that minimizes both classification error and variance across data distributions. Comprehensive experimental validation on benchmark datasets confirms the effectiveness of DMLITE, achieving classification accuracies of 98.87\%, 92.61\%, and 99.83\% on USTC-TFC, ISCX-VPN, and Edge-IIoTset datasets, respectively. This improves classification accuracy by an average of 3.7\% and reduces training time by an average of 41.9\% compared to the representative deep learning model.

cs.NI↗

arXiv2025

A Survey on Reconfigurable Intelligent Surfaces in Practical Systems: Security and Privacy Perspectives

Reconfigurable Intelligent Surfaces (RIS) have emerged as a transformative technology capable of reshaping wireless environments through dynamic manipulation of electromagnetic waves. While extensive research has explored their theoretical benefits for communication and sensing, practical deployments in smart environments such as homes, vehicles, and industrial settings remain limited and under-examined, particularly from security and privacy perspectives. This survey provides a comprehensive examination of RIS applications in real-world systems, with a focus on the security and privacy threats, vulnerabilities, and defensive strategies relevant to practical use. We analyze scenarios with two types of systems (with and without legitimate RIS) and two types of attackers (with and without malicious RIS), and demonstrate how RIS may introduce new attacks to practical systems, including eavesdropping, jamming, and spoofing attacks. In response, we review defenses against RIS-related attacks in these systems, such as applying additional security algorithms, disrupting attackers, and early detection of unauthorized RIS. We also discuss scenarios in which the legitimate user applies an additional RIS to defend against attacks. To support future research, we also provide a collection of open-source tools, datasets, demos, and papers at: https://awesome-ris-security.github.io/. By highlighting RIS's functionality and its security/privacy challenges and opportunities, this survey aims to guide researchers and engineers toward the development of secure, resilient, and privacy-preserving RIS-enabled practical wireless systems and environments.

cs.CR↗

arXiv2025

Tutorial on Large Language Model-Enhanced Reinforcement Learning for Wireless Networks

Reinforcement Learning (RL) has shown remarkable success in enabling adaptive and data-driven optimization for various applications in wireless networks. However, classical RL suffers from limitations in generalization, learning feedback, interpretability, and sample efficiency in dynamic wireless environments. Large Language Models (LLMs) have emerged as a transformative Artificial Intelligence (AI) paradigm with exceptional capabilities in knowledge generalization, contextual reasoning, and interactive generation, which have demonstrated strong potential to enhance classical RL. This paper serves as a comprehensive tutorial on LLM-enhanced RL for wireless networks. We propose a taxonomy to categorize the roles of LLMs into four critical functions: state perceiver, reward designer, decision-maker, and generator. Then, we review existing studies exploring how each role of LLMs enhances different stages of the RL pipeline. Moreover, we provide a series of case studies to illustrate how to design and apply LLM-enhanced RL in low-altitude economy networking, vehicular networks, and space-air-ground integrated networks. Finally, we conclude with a discussion on potential future directions for LLM-enhanced RL and offer insights into its future development in wireless networks.

cs.NI↗

arXiv2025

FAST: Flexible and Adaptive Semantic Transmission for Resource-constrained Multi-user Generative Semantic Communication

The rapid advancement of generative artificial intelligence has spurred innovative approaches to semantic communication, giving rise to a new paradigm known as generative semantic communication (GSC). The integration of flexible cross-modal semantic extraction with generative capability-driven semantic inference substantially enhances semantic compression efficiency, demonstrating significant promise under communication resource constraints. Nonetheless, the stringent dependence on high computational power and the resulting latency continue to present major challenges, thereby limiting the feasibility of large-scale deployment. To address these challenges, we propose a novel GSC framework named FAST, which stands for flexible and adaptive semantic transmission. To accommodate limited computational resources, we propose a sequential semantic extraction method, where a temporal prompt engineering module orchestrates the distillation and transmission of key semantic units. Correspondingly, we introduce a sequential conditional denoising module at the receiver, which adapts the diffusion-based reconstruction to the progressively received input. To enhance overall task performance in multi-user semantic transmission, we propose a semantic-aware resource allocation method that optimizes bandwidth dynamically based on a joint consideration of semantic dependencies, user-level task priorities, and instantaneous channel conditions. Extensive experiments demonstrate that the proposed architecture achieves system precision comparable to conventional GSC systems while significantly reducing transmission latency and improving overall efficiency. These results confirm its enhanced potential for deployment in multi-user GSC scenarios with stringent communication and computational constraints.

eess.SP↗

arXiv2025

Low-Altitude UAV-Carried Movable Antenna for Joint Wireless Power Transfer and Covert Communications

The proliferation of Internet of Things (IoT) networks has created an urgent need for sustainable energy solutions, particularly for the battery-constrained spatially distributed IoT nodes. While low-altitude uncrewed aerial vehicles (UAVs) employed with wireless power transfer (WPT) capabilities offer a promising solution, the line-of-sight channels that facilitate efficient energy delivery also expose sensitive operational data to adversaries. This paper proposes a novel low-altitude UAV-carried movable antenna-enhanced transmission system joint WPT and covert communications, which simultaneously performs energy supplements to IoT nodes and establishes transmission links with a covert user by leveraging wireless energy signals as a natural cover. Then, we formulate a multi-objective optimization problem that jointly maximizes the total harvested energy of IoT nodes and sum achievable rate of the covert user, while minimizing the propulsion energy consumption of the low-altitude UAV. To address the non-convex and temporally coupled optimization problem, we propose a mixture-of-experts-augmented soft actor-critic (MoE-SAC) algorithm that employs a sparse Top-K gated mixture-of-shallow-experts architecture to represent multimodal policy distributions arising from the conflicting optimization objectives. We also incorporate an action projection module that explicitly enforces per-time-slot power budget constraints and antenna position constraints. Simulation results demonstrate that the proposed approach significantly outperforms some baseline approaches and other state-of-the-art deep reinforcement learning algorithms.

cs.NI↗

arXiv2025

When UAV Swarm Meets IRS: Collaborative Secure Communications in Low-altitude Wireless Networks

Low-altitude wireless networks (LAWNs) represent a promising architecture that integrates unmanned aerial vehicles (UAVs) as aerial nodes to provide enhanced coverage, reliability, and throughput for diverse applications. However, these networks face significant security vulnerabilities from both known and potential unknown eavesdroppers, which may threaten data confidentiality and system integrity. To solve this critical issue, we propose a novel secure communication framework for LAWNs where the selected UAVs within a swarm function as a virtual antenna array (VAA), complemented by intelligent reflecting surface (IRS) to create a robust defense against eavesdropping attacks. Specifically, we formulate a multi-objective optimization problem that simultaneously maximizes the secrecy rate while minimizing the maximum sidelobe level and total energy consumption, requiring joint optimization of UAV excitation current weights, flight trajectories, and IRS phase shifts. This problem presents significant difficulties due to the dynamic nature of the system and heterogeneous components. Thus, we first transform the problem into a heterogeneous Markov decision process (MDP). Then, we propose a heterogeneous multi-agent control approach (HMCA) that integrates a dedicated IRS control policy with a multi-agent soft actor-critic framework for UAV control, which enables coordinated operation across heterogeneous network elements. Simulation results show that the proposed HMCA achieves superior performance compared to baseline approaches in terms of secrecy rate improvement, sidelobe suppression, and energy efficiency. Furthermore, we find that the collaborative and passive beamforming synergy between VAA and IRS creates robust security guarantees when the number of UAVs increases.

cs.NI↗

arXiv2025

From Agentification to Self-Evolving Agentic AI for Wireless Networks: Concepts, Approaches, and Future Research Directions

Self-evolving agentic artificial intelligence (AI) offers a new paradigm for future wireless systems by enabling autonomous agents to continually adapt and improve without human intervention. Unlike static AI models, self-evolving agents embed an autonomous evolution cycle that updates models, tools, and workflows in response to environmental dynamics. This paper presents a comprehensive overview of self-evolving agentic AI, highlighting its layered architecture, life cycle, and key techniques, including tool intelligence, workflow optimization, self-reflection, and evolutionary learning. We further propose a multi-agent cooperative self-evolving agentic AI framework, where multiple large language models (LLMs) are assigned role-specialized prompts under the coordination of a supervisor agent. Through structured dialogue, iterative feedback, and systematic validation, the system autonomously executes the entire life cycle without human intervention. A case study on antenna evolution in low-altitude wireless networks (LAWNs) demonstrates how the framework autonomously upgrades fixed antenna optimization into movable antenna optimization. Experimental results show that the proposed self-evolving agentic AI autonomously improves beam gain and restores degraded performance by up to 52.02%, consistently surpassing the fixed baseline with little to no human intervention and validating its adaptability and robustness for next-generation wireless intelligence.

cs.AI↗

arXiv2025

Resource-Aware LLM Reasoning for Mobile Edge General Intelligence

The rapid advancement of large language models (LLMs) has enabled an emergence of agentic artificial intelligence (AI) with powerful reasoning and autonomous decision-making capabilities. This integration with edge computing has led to the development of Mobile Edge General Intelligence (MEGI), which brings real-time, privacy-preserving reasoning to the network edge. However, deploying LLM-based agentic AI reasoning in MEGI environments poses significant challenges due to the high computational demands of reasoning and the limited resources of edge devices. To address these challenges, we propose a joint optimization framework for efficient LLM reasoning deployment in MEGI. First, we systematically review enhancement methods to identify mechanisms suitable for edge adaptation. Subsequently, we present a distributed framework that synergizes reasoning enhancement via adaptive CoT prompting with scalable deployment through a distributed MoE architecture. An important innovation of this approach involves modeling reasoning depth as a dynamic network resource variable, which is optimized jointly with expert activation and transmission power. This mechanism allows the system to dynamically regulate expert networks and reasoning complexity according to task requirements and device capabilities. Experimental evaluations in mobile edge environments demonstrate that the proposed framework effectively balances reasoning quality and resource efficiency. The results show that with less than one second of additional inference time, both accuracy and latency satisfaction rate can reach 90\%, validating the practical viability of deploying sophisticated LLM reasoning in resource-constrained MEGI systems.

cs.AI↗