HDHongyang Du

Hongyang Du

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Hongyang Du has a total of 99 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Diffusion-Modeled Reinforcement Learning for Carbon and Risk-Aware Microgrid Optimization

    by Yunyi Zhao, Wei Zhang, Cheng Xiang, Hongyang Du, Dusit Niyato, Shuhua Gao

  • Open Access

    How to Make Tool-Using LLM Agents Efficient? A Survey

    by Yunuo Hu, Ziyang Cheng, Wenqi Pei, Miaomiao Li, Boyan Li, Yizhang Zhu, Yupeng Xie, Han Chen, Shizheng Hou, Yuyu Luo, et al.

    Large language models (LLMs) are increasingly deployed as agents that leverage external tools to resolve complex tasks, transcending the limitations of static parametric knowledge. However, tool-using LLM agents often rely on extended context, multi-step reasoning, and frequent tool interactions, incurring substantial computational and financial resources. As a result, efficient tool-using LLM agents that could reduce one or more forms of resource consumption while maintaining comparable task performance have attracted growing research attention. Nevertheless, existing efforts remain fragmented across different stages and resource dimensions. To address this gap, this survey presents a systematic review and a unified taxonomy of efficient tool-using LLM agents. We categorize efficiency techniques along four stages of the agent loop: (i) Efficient Tool Context, (ii) Efficient Tool Calling, (iii) Efficient Tool Reasoning, and (iv) Efficient Tool Execution. By analyzing these methods, we reveal their shared mechanisms and limitations, identify critical open challenges, and highlight promising directions for future research. This survey provides a foundational roadmap to accelerate the development of efficient tool-using LLM agents.

  • Open Access

    GLOVE: Global Verifier for LLM Memory-Environment Realignment

    by Xingkun Yin, Hongyang Du

    Most existing memory-enhanced Large Language Model (LLM) approaches implicitly assume that memory validity can be established either through external evaluators that provide task-specific success signals or through internal model cognition, such as reflection, for editing memory entries. However, these assumptions often break down in practical environments with dynamic drifts. We propose the Global Verifier (GLOVE), a framework that introduces a new design dimension for LLM memory systems by establishing a relative notion of truth. Through active probing to detect inconsistencies between retrieved memories and fresh observations, GLOVE enables memory-environment realignment by verifying and updating memory without access to ground-truth supervision or strong reliance on model introspection. We evaluate GLOVE on diverse benchmarks spanning web navigation, planning, and control, augmented with controlled environmental drifts that introduce non-stationarity beyond the original benchmark settings. Our results show that GLOVE substantially improves agent success rates, suggesting a robust pathway to cognitive agents capable of self-evolving.

  • Open Access

    U-MASK: User-adaptive Spatio-Temporal Masking for Personalized Mobile AI Applications

    by Shiyuan Zhang, Yilai Liu, Yuwei Du, Ruoxuan Yang, Dong In Kim, Hongyang Du

    Personalized mobile artificial intelligence applications are widely deployed, yet they are expected to infer user behavior from sparse and irregular histories under a continuously evolving spatio-temporal context. This setting induces a fundamental tension among three requirements, i.e., immediacy to adapt to recent behavior, stability to resist transient noise, and generalization to support long-horizon prediction and cold-start users. Most existing approaches satisfy at most two of these requirements, resulting in an inherent impossibility triangle in data-scarce, non-stationary personalization. To address this challenge, we model mobile behavior as a partially observed spatio-temporal tensor and unify short-term adaptation, long-horizon forecasting, and cold-start recommendation as a conditional completion problem, where a user- and task-specific mask specifies which coordinates are treated as evidence. We propose U-MASK, a user-adaptive spatio-temporal masking method that allocates evidence budgets based on user reliability and task sensitivity. To enable mask generation under sparse observations, U-MASK learns a compact, task-agnostic user representation from app and location histories via U-SCOPE, which serves as the sole semantic conditioning signal. A shared diffusion transformer then performs mask-guided generative completion while preserving observed evidence, so personalization and task differentiation are governed entirely by the mask and the user representation. Experiments on real-world mobile datasets demonstrate consistent improvements over state-of-the-art methods across short-term prediction, long-horizon forecasting, and cold-start settings, with the largest gains under severe data sparsity. The code and dataset will be available at https://github.com/NICE-HKU/U-MASK.

  • Open Access

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

    by Xudong Wang, Lei Feng, Ruichen Zhang, Fanqin Zhou, Hongyang Du, Wenjing Li, Dusit Niyato, Abbas Jamalipour, Ping Zhang

    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.

  • Open Access

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

    by Changyuan Zhao, Jiacheng Wang, Ruichen Zhang, Dusit Niyato, Hongyang Du, Zehui Xiong, Dong In Kim, Ping Zhang

    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.

  • Open Access

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

    by Anbang Zhang, Shuaishuai Guo, Chenyuan Feng, Hongyang Du, Haojin Li, Chen Sun, Haijun Zhang

    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.

  • Open Access

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

    by Yongjie Zeng, Hongyang Du

    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.

  • Open Access

    LSDM: LLM-Enhanced Spatio-temporal Diffusion Model for Service-Level Mobile Traffic Prediction

    by Shiyuan Zhang, Tong Li, Zhu Xiao, Hongyang Du, Kaibin Huang

    Service-level mobile traffic prediction for individual users is essential for network efficiency and quality of service enhancement. However, current prediction methods are limited in their adaptability across different urban environments and produce inaccurate results due to the high uncertainty in personal traffic patterns, the lack of detailed environmental context, and the complex dependencies among different network services. These challenges demand advanced modeling techniques that can capture dynamic traffic distributions and rich environmental features. Inspired by the recent success of diffusion models in distribution modeling and Large Language Models (LLMs) in contextual understanding, we propose an LLM-Enhanced Spatio-temporal Diffusion Model (LSDM). LSDM integrates the generative power of diffusion models with the adaptive learning capabilities of transformers, augmented by the ability to capture multimodal environmental information for modeling service-level patterns and dynamics. Extensive evaluations on real-world service-level datasets demonstrate that the model excels in traffic usage predictions, showing outstanding generalization and adaptability. After incorporating contextual information via LLM, the performance improves by at least 2.83% in terms of the coefficient of determination. Compared to models of a similar type, such as CSDI, the root mean squared error can be reduced by at least 8.29%. The code and dataset will be available at: https://github.com/SoftYuaneR/LSDM.

  • Open Access

    Diffusion-Modeled Reinforcement Learning for Carbon and Risk-Aware Microgrid Optimization

    by Yunyi Zhao, Wei Zhang, Cheng Xiang, Hongyang Du, Dusit Niyato, Shuhua Gao

    This paper introduces DiffCarl, a diffusion-modeled carbon- and risk-aware reinforcement learning algorithm for intelligent operation of multi-microgrid systems. With the growing integration of renewables and increasing system complexity, microgrid communities face significant challenges in real-time energy scheduling and optimization under uncertainty. DiffCarl integrates a diffusion model into a deep reinforcement learning (DRL) framework to enable adaptive energy scheduling under uncertainty and explicitly account for carbon emissions and operational risk. By learning action distributions through a denoising generation process, DiffCarl enhances DRL policy expressiveness and enables carbon- and risk-aware scheduling in dynamic and uncertain microgrid environments. Extensive experimental studies demonstrate that it outperforms classic algorithms and state-of-the-art DRL solutions, with 2.3-30.1% lower operational cost. It also achieves 28.7% lower carbon emissions than those of its carbon-unaware variant and reduces performance variability. These results highlight DiffCarl as a practical and forward-looking solution. Its flexible design allows efficient adaptation to different system configurations and objectives to support real-world deployment in evolving energy systems.