arXiv subjects

Hongyang Du

Publications and source records attributed to Hongyang Du.

At least 55 records · Page 3Linked to original sources

arXiv2025

LLM-Empowered Agentic AI for QoE-Aware Network Slicing Management in Industrial IoT

The Industrial Internet of Things (IIoT) requires networks that deliver ultra-low latency, high reliability, and cost efficiency, which traditional optimization methods and deep reinforcement learning (DRL)-based approaches struggle to provide under dynamic and heterogeneous workloads. To address this gap, large language model (LLM)-empowered agentic AI has emerged as a promising paradigm, integrating reasoning, planning, and adaptation to enable QoE-aware network management. In this paper, we explore the integration of agentic AI into QoE-aware network slicing for IIoT. We first review the network slicing management architecture, QoE metrics for IIoT applications, and the challenges of dynamically managing heterogeneous network slices, while highlighting the motivations and advantages of adopting agentic AI. We then present the workflow of agentic AI-based slicing management, illustrating the full lifecycle of AI agents from processing slice requests to constructing slice instances and performing dynamic adjustments. Furthermore, we propose an LLM-empowered agentic AI approach for slicing management, which integrates a retrieval-augmented generation (RAG) module for semantic intent inference, a DRL-based orchestrator for slicing configuration, and an incremental memory mechanism for continual learning and adaptation. Through a case study on heterogeneous slice management, we demonstrate that the proposed approach significantly outperforms other baselines in balancing latency, reliability, and cost, and achieves up to a 19% improvement in slice availability ratio.

cs.NI↗

arXiv2025

Large Language Model Empowered Next-Generation MIMO Networks: Fundamentals, Challenges, and Visions

Next-generation Multiple-Input Multiple-Output (MIMO) is expected to be intelligent and scalable. In this paper, we study Large Language Model (LLM)-enabled next-generation MIMO networks. Firstly, we provide an overview of the development, fundamentals, and challenges of the next-generation MIMO. Then, we propose the concept of the generative AI agent, which is capable of generating tailored and specialized contents with the aid of LLM and Retrieval Augmented Generation (RAG). Next, we comprehensively discuss the features and advantages of the generative AI agent framework. More importantly, to tackle existing challenges of next-generation MIMO, we discuss generative AI agent-enabled next-generation MIMO networks from the perspective of performance analysis, signal processing, and resource allocation. Furthermore, we present two compelling case studies that demonstrate the effectiveness of leveraging the generative AI agent for performance analysis in complex configuration scenarios. These examples highlight how the integration of generative AI agents can significantly enhance the analysis and design of next-generation MIMO systems. Finally, we discuss important potential research future directions.

cs.NI↗

arXiv2025

SecDiff: Diffusion-Aided Secure Deep Joint Source-Channel Coding Against Adversarial Attacks

Deep joint source-channel coding (JSCC) has emerged as a promising paradigm for semantic communication, delivering significant performance gains over conventional separate coding schemes. However, existing JSCC frameworks remain vulnerable to physical-layer adversarial threats, such as pilot spoofing and subcarrier jamming, compromising semantic fidelity. In this paper, we propose SecDiff, a plug-and-play, diffusion-aided decoding framework that significantly enhances the security and robustness of deep JSCC under adversarial wireless environments. Different from prior diffusion-guided JSCC methods that suffer from high inference latency, SecDiff employs pseudoinverse-guided sampling and adaptive guidance weighting, enabling flexible step-size control and efficient semantic reconstruction. To counter jamming attacks, we introduce a power-based subcarrier masking strategy and recast recovery as a masked inpainting problem, solved via diffusion guidance. For pilot spoofing, we formulate channel estimation as a blind inverse problem and develop an expectation-minimization (EM)-driven reconstruction algorithm, guided jointly by reconstruction loss and a channel operator. Notably, our method alternates between pilot recovery and channel estimation, enabling joint refinement of both variables throughout the diffusion process. Extensive experiments over orthogonal frequency-division multiplexing (OFDM) channels under adversarial conditions show that SecDiff outperforms existing secure and generative JSCC baselines by achieving a favorable trade-off between reconstruction quality and computational cost. This balance makes SecDiff a promising step toward practical, low-latency, and attack-resilient semantic communications.

cs.CV↗

arXiv2025

VideoHallu: Evaluating and Mitigating Multi-modal Hallucinations on Synthetic Video Understanding

Vision-Language Models (VLMs) have achieved strong results in video understanding, yet a key question remains: do they truly comprehend visual content or only learn shallow correlations between vision and language? Real visual understanding, especially of physics and common sense, is essential for AI systems that interact with the physical world. Current evaluations mostly use real-world videos similar to training data, so high benchmark scores may not reflect real reasoning ability. To address this, we propose negative-control tests using videos that depict physically impossible or logically inconsistent events. We introduce VideoHallu, a synthetic dataset of physics- and commonsense-violating scenes generated with Veo2, Sora, and Kling. It includes expert-annotated question-answer pairs across four categories of violations. Tests of leading VLMs (Qwen-2.5-VL, Video-R1, VideoChat-R1) show that, despite strong results on benchmarks such as MVBench and MMVU, they often miss these violations, exposing gaps in visual reasoning. Reinforcement learning fine-tuning on VideoHallu improves recognition of such violations without reducing standard benchmark performance. Our data is available at https://github.com/zli12321/VideoHallu.git.

cs.CV↗

arXiv2025

JAUNT: Joint Alignment of User Intent and Network State for QoE-centric LLM Tool Routing

Large Language Models (LLMs) increasingly rely on emerging protocols such as the Model Context Protocol (MCP) to invoke external tools and services. However, current tool routing mechanisms remain fragile because they only consider functional matching between users' queries and tools. In practice, user intent expressed through queries can be vague or underspecified, and the actual Quality of Experience (QoE) also depends on external factors such as link latency and server availability that are not captured by semantics alone. To address this challenge, we propose JAUNT, a framework for Joint Alignment of User intent and Network state in QoE-centric Tool routing. JAUNT introduces a dual-view alignment strategy that interprets user intent while employing LLM agents to construct network profiles, mapping numerical performance indicators into the semantic space to guide routing. We further design a benchmark that integrates diverse user request patterns with heterogeneous network states, enabling systematic evaluation of QoE outcomes. Experimental results show that JAUNT significantly improves QoE compared with several baselines, demonstrating the importance of aligning both intent and network state for scalable LLM service orchestration.

cs.NI↗

arXiv2025

NetMCP: Network-Aware Model Context Protocol Platform for LLM Capability Extension

Large Language Models (LLMs) remain static in functionality after training, and extending their capabilities requires integration with external data, computation, and services. The Model Context Protocol (MCP) has emerged as a standard interface for such extensions, but current implementations rely solely on semantic matching between users' requests and server function descriptions, which makes current deployments and simulation testbeds fragile under latency fluctuations or server failures. We address this gap by enhancing MCP tool routing algorithms with real-time awareness of network and server status. To provide a controlled test environment for development and evaluation, we construct a heterogeneous experimental platform, namely Network-aware MCP (NetMCP), which offers five representative network states and build a benchmark for latency sequence generation and MCP server datasets. On top of NetMCP platform, we analyze latency sequences and propose a Semantic-Oriented and Network-Aware Routing (SONAR) algorithm, which jointly optimizes semantic similarity and network Quality of Service (QoS) metrics for adaptive tool routing. Results show that SONAR consistently improves task success rate and reduces completion time and failure number compared with semantic-only, LLM-based baselines, demonstrating the value of network-aware design for production-scale LLM systems. The code for NetMCP is available at https://github.com/NICE-HKU/NetMCP.

cs.NI↗

arXiv2025

Experience Scaling: Post-Deployment Evolution For Large Language Models

Scaling model size, training data, and compute power have driven advances in large language models (LLMs), but these approaches are reaching saturation as human-generated text is exhausted and further gains diminish. We propose experience scaling, a framework for continuous post-deployment evolution for LLMs through autonomous interaction with the environment and collaborative sharing of accumulated experience. The framework captures raw interactions, distills them into compact, reusable knowledge, and periodically refines stored content to preserve relevance and efficiency. We validate the framework in simulated real-world scenarios involving generalization to previously unseen but related tasks, repetitive queries, and over-saturated knowledge stores. Across all settings, experience scaling improves accuracy, sustains performance over time, and maintains gains when applied to novel situations. These results demonstrate that structured post-deployment learning can extend LLM capabilities beyond the limits of static human-generated data, offering a scalable path for continued intelligence progress.

cs.AI↗

arXiv2025

Ubiquitous Intelligence Via Wireless Network-Driven LLMs Evolution

We introduce ubiquitous intelligence as a paradigm where Large Language Models (LLMs) evolve within wireless network-driven ecosystems. Unlike static model deployments, this approach enables scalable and continuous intelligence ascension through coordination between networks and LLMs. Wireless networks support system-orchestrated lifelong learning, while LLMs drive the next-generation network development that is more adaptive and responsive. This co-evolution highlights a shift toward self-improving systems, sustaining capability growth across diverse and resource-constrained environments.

cs.NI↗

arXiv2025

Secure Multi-LLM Agentic AI and Agentification for Edge General Intelligence by Zero-Trust: A Survey

Agentification serves as a critical enabler of Edge General Intelligence (EGI), transforming massive edge devices into cognitive agents through integrating Large Language Models (LLMs) and perception, reasoning, and acting modules. These agents collaborate across heterogeneous edge infrastructures, forming multi-LLM agentic AI systems that leverage collective intelligence and specialized capabilities to tackle complex, multi-step tasks. However, the collaborative nature of multi-LLM systems introduces critical security vulnerabilities, including insecure inter-LLM communications, expanded attack surfaces, and cross-domain data leakage that traditional perimeter-based security cannot adequately address. To this end, this survey introduces zero-trust security of multi-LLM in EGI, a paradigmatic shift following the ``never trust, always verify'' principle. We begin by systematically analyzing the security risks in multi-LLM systems within EGI contexts. Subsequently, we present the vision of a zero-trust multi-LLM framework in EGI. We then survey key technical progress to facilitate zero-trust multi-LLM systems in EGI. Particularly, we categorize zero-trust security mechanisms into model- and system-level approaches. The former and latter include strong identification, context-aware access control, etc., and proactive maintenance, blockchain-based management, etc., respectively. Finally, we identify critical research directions. This survey serves as the first systematic treatment of zero-trust applied to multi-LLM systems, providing both theoretical foundations and practical strategies.

cs.NI↗

arXiv2025

Maximum-Likelihood Estimation Based on Diffusion Model For Wireless Communications

Generative Artificial Intelligence (GenAI) models, with their powerful feature learning capabilities, have been applied in many fields. In mobile wireless communications, GenAI can dynamically optimize the network to enhance the user experience. Especially in signal detection and channel estimation tasks, due to digital signals following a certain random distribution, GenAI models can fully utilize their distribution learning characteristics. For example, diffusion models (DMs) and normalized flow models have been applied to related tasks. However, since the DM cannot guarantee that the generated results are the maximum-likelihood estimation points of the distribution during the data generation process, the successful task completion rate is reduced. Based on this, this paper proposes a Maximum-Likelihood Estimation Inference (MLEI) framework. The framework uses the loss function in the forward diffusion process of the DM to infer the maximum-likelihood estimation points in the discrete space. Then, we present a signal detection task in near-field communication scenarios with unknown noise characteristics. In experiments, numerical results demonstrate that the proposed framework has better performance than state-of-the-art signal estimators.

eess.SP↗

arXiv2025

Generative Feature Imputing -- A Technique for Error-resilient Semantic Communication

Semantic communication (SemCom) has emerged as a promising paradigm for achieving unprecedented communication efficiency in sixth-generation (6G) networks by leveraging artificial intelligence (AI) to extract and transmit the underlying meanings of source data. However, deploying SemCom over digital systems presents new challenges, particularly in ensuring robustness against transmission errors that may distort semantically critical content. To address this issue, this paper proposes a novel framework, termed generative feature imputing, which comprises three key techniques. First, we introduce a spatial error concentration packetization strategy that spatially concentrates feature distortions by encoding feature elements based on their channel mappings, a property crucial for both the effectiveness and reduced complexity of the subsequent techniques. Second, building on this strategy, we propose a generative feature imputing method that utilizes a diffusion model to efficiently reconstruct missing features caused by packet losses. Finally, we develop a semantic-aware power allocation scheme that enables unequal error protection by allocating transmission power according to the semantic importance of each packet. Experimental results demonstrate that the proposed framework outperforms conventional approaches, such as Deep Joint Source-Channel Coding (DJSCC) and JPEG2000, under block fading conditions, achieving higher semantic accuracy and lower Learned Perceptual Image Patch Similarity (LPIPS) scores.

cs.LG↗

arXiv2025

Spectral Efficiency-Aware Codebook Design for Task-Oriented Semantic Communications

Digital task-oriented semantic communication (ToSC) aims to transmit only task-relevant information, significantly reducing communication overhead. Existing ToSC methods typically rely on learned codebooks to encode semantic features and map them to constellation symbols. However, these codebooks are often sparsely activated, resulting in low spectral efficiency and underutilization of channel capacity. This highlights a key challenge: how to design a codebook that not only supports task-specific inference but also approaches the theoretical limits of channel capacity. To address this challenge, we construct a spectral efficiency-aware codebook design framework that explicitly incorporates the codebook activation probability into the optimization process. Beyond maximizing task performance, we introduce the Wasserstein (WS) distance as a regularization metric to minimize the gap between the learned activation distribution and the optimal channel input distribution. Furthermore, we reinterpret WS theory from a generative perspective to align with the semantic nature of ToSC. Combining the above two aspects, we propose a WS-based adaptive hybrid distribution scheme, termed WS-DC, which learns compact, task-driven and channel-aware latent representations. Experimental results demonstrate that WS-DC not only outperforms existing approaches in inference accuracy but also significantly improves codebook efficiency, offering a promising direction toward capacity-approaching semantic communication systems.

eess.SP↗

arXiv2025

Task Offloading and Resource Allocation for MEC-assisted Consumer Internet of Vehicle Systems

Mobile edge computing (MEC)-assisted internet of vehicle (IoV) is emerging as a promising paradigm to provide computing services for vehicles. However, meeting the computing-sensitive and computation-intensive demands of vehicles poses several challenges, including the discrepancy between the limited resource provision and stringent computing requirement, the difficulty in capturing and integrating the intricate features of the MEC-assisted IoV system into the problem formulation, and the need for real-time processing and efficient resource management in the dynamic environment. In this work, we explore the AI-enabled task offloading and resource allocation for MEC-assisted consumer IoV systems. Specifically, we first present a multi-MEC-assisted consumer IoV architecture that leverages the computational resources of MEC servers to provide offloading services close to vehicles. Subsequently, we formulate a system cost minimization optimization problem (SCMOP) by integrating the service delay and energy consumption. To efficiently solve this problem, we design a joint task offloading and computing resource allocation approach (JTOCRA) by applying the multi-agent deep deterministic policy gradient (MADDPG) algorithm. Finally, simulation results demonstrate that the proposed JTOCRA can achieve superior system performances and exhibits better scalability compared to other alternative approaches.

cs.NI↗

arXiv2025

User-Intent-Driven Semantic Communication via Adaptive Deep Understanding

Semantic communication focuses on transmitting task-relevant semantic information, aiming for intent-oriented communication. While existing systems improve efficiency by extracting key semantics, they still fail to deeply understand and generalize users' real intentions. To overcome this, we propose a user-intention-driven semantic communication system that interprets diverse abstract intents. First, we integrate a multi-modal large model as semantic knowledge base to generate user-intention prior. Next, a mask-guided attention module is proposed to effectively highlight critical semantic regions. Further, a channel state awareness module ensures adaptive, robust transmission across varying channel conditions. Extensive experiments demonstrate that our system achieves deep intent understanding and outperforms DeepJSCC, e.g., under a Rayleigh channel at an SNR of 5 dB, it achieves improvements of 8%, 6%, and 19% in PSNR, SSIM, and LPIPS, respectively.

cs.IT↗

arXiv2025

Less Signals, More Understanding: Channel-Capacity Codebook Design for Digital Task-Oriented Semantic Communication

Discrete representation has emerged as a powerful tool in task-oriented semantic communication (ToSC), offering compact, interpretable, and efficient representations well-suited for low-power edge intelligence scenarios. Its inherent digital nature aligns seamlessly with hardware-friendly deployment and robust storage/transmission protocols. However, despite its strengths, current ToSC frameworks often decouple semantic-aware discrete mapping from the underlying channel characteristics and task demands. This mismatch leads to suboptimal communication performance, degraded task utility, and limited generalization under variable wireless conditions. Moreover, conventional designs frequently overlook channel-awareness in codebook construction, restricting the effectiveness of semantic symbol selection under constrained resources. To address these limitations, this paper proposes a channel-aware discrete semantic coding framework tailored for low-power edge networks. Leveraging a Wasserstein-regularized objective, our approach aligns discrete code activations with optimal input distributions, thereby improving semantic fidelity, robustness, and task accuracy. Extensive experiments on the inference tasks across diverse signal-to-noise ratio (SNR) regimes show that our method achieves notable gains in accuracy and communication efficiency. This work provides new insights into integrating discrete semantics and channel optimization, paving the way for the widespread adoption of semantic communication in future digital infrastructures.

eess.SP↗

arXiv2025

M3LLM: Model Context Protocol-aided Mixture of Vision Experts For Multimodal LLMs in Networks

Current Multimodal Large Language Models (MLLMs) rely on centralized architectures and often suffer from poor alignment between the input task and their fixed visual encoding modules, which limits performance on diverse and dynamic visual tasks. With the increasing deployment of resource-efficient models on edge devices in wireless networks, a new opportunity emerges to dynamically use distributed vision experts for improved MLLM inference quality. To enable this, we propose M3LLM, where the Model Context Protocol (MCP) coordinates a mixture of vision experts to achieve distributed MLLMs. Specifically, MCP is an open protocol that structures the input task context into interpretable representations, enabling wireless network-aware coordination between the central model backbone and edge-hosted vision experts. Based on the MCP representation, M3LLM formulates vision expert routing as a joint optimization problem that balances task-expert semantic compatibility and channel performance. To solve the resulting gradient conflicts, we develop a dual-stream Soft Actor-Critic (SAC) algorithm with decoupled reward signals and introduce an Adaptive Stability Enhancement Module (ASEM) based on hierarchical Bayesian modeling to ensure effective routing. Experiments show that M3LLM improves task accuracy, reduces communication cost, and enhances expert routing adaptability under dynamic wireless network conditions.

cs.NI↗

arXiv2025

Joint Association and Phase Shifts Design for UAV-mounted Stacked Intelligent Metasurfaces-assisted Communications

Stacked intelligent metasurfaces (SIMs) have emerged as a promising technology for realizing wave-domain signal processing, while the fixed SIMs will limit the communication performance of the system compared to the mobile SIMs. In this work, we consider a UAV-mounted SIMs (UAV-SIMs) assisted communication system, where UAVs as base stations (BSs) can cache the data processed by SIMs, and also as mobile vehicles flexibly deploy SIMs to enhance the communication performance. To this end, we formulate a UAV-SIM-based joint optimization problem (USBJOP) to comprehensively consider the association between UAV-SIMs and users, the locations of UAV-SIMs, and the phase shifts of UAV-SIMs, aiming to maximize the network capacity. Due to the non-convexity and NP-hardness of USBJOP, we decompose it into three sub-optimization problems, which are the association between UAV-SIMs and users optimization problem (AUUOP), the UAV location optimization problem (ULOP), and the UAV-SIM phase shifts optimization problem (USPSOP). Then, these three sub-optimization problems are solved by an alternating optimization (AO) strategy. Specifically, AUUOP and ULOP are transformed to a convex form and then solved by the CVX tool, while we employ a layer-by-layer iterative optimization method for USPSOP. Simulation results verify the effectiveness of the proposed strategy under different simulation setups.

cs.NI↗

arXiv2025

Generative AI-enabled Wireless Communications for Robust Low-Altitude Economy Networking

Low-Altitude Economy Networks (LAENets) have emerged as significant enablers of social activities, offering low-altitude services such as the transportation of packages, groceries, and medical supplies. Owing to their control mechanisms and ever-changing operational factors, LAENets are inherently more complex and vulnerable to security threats than traditional terrestrial networks. As applications of LAENet continue to expand, the robustness of these systems becomes crucial. In this paper, we propose a generative artificial intelligence (GenAI) optimization framework that tackles robustness challenges in LAENets. We conduct a systematic analysis of robustness requirements for LAENets, complemented by a comprehensive review of robust Quality of Service (QoS) metrics from the wireless physical layer perspective. We then investigate existing GenAI-enabled approaches for robustness enhancement. This leads to our proposal of a novel diffusion-based optimization framework with a Mixture of Experts (MoE)-transformer actor network. In the robust beamforming case study, the proposed framework demonstrates its effectiveness by optimizing beamforming under uncertainties, achieving a more than 15% increase over four learning baselines in the worst-case achievable secrecy rate. These findings highlight the significant potential of GenAI in strengthening LAENet robustness.

eess.SP↗