arXiv subjects

Haiyuan Li

Publications and source records attributed to Haiyuan Li.

11 recordsLinked to original sources

arXiv2026

A Low-Latency Semantic State Estimator using Latent Predictive Learning for Dynamic Network Monitoring and Orchestration

Closed-loop network monitoring and orchestration increasingly require semantic interpretations of live telemetry beyond raw counter collection. However, dynamic cloud-edge environments change both the active node set and the monitoring query at runtime, while control loops demand bounded millisecond-scale responses. We introduce a latent predictive state estimator (LPSE) for dynamic network monitoring and orchestration, built on latent predictive learning over streaming telemetry. The framework converts variable-cardinality node telemetry into topology-adaptive temporal representations, fuses them with monitoring questions, and returns bounded answers from a semantic codebook instead of autoregressive text generation. This design enables fixed-cost, single-pass inference while preserving semantic interpretability. By operating on permutation-invariant, slot-routed node representations keyed by stable identity, the model maintains a fixed input space and generalizes to node addition, removal, and reordering without retraining. Experimental results on a multi-node Kubernetes cluster show semantic prediction accuracy of 87.13% at approximately 72x lower mean inference latency compared to the lowest latency LLM tested.

cs.DC↗

arXiv2026

Deadline-Driven Hierarchical Agentic Resource Sharing for AI Services and RAN Functions in AI-RAN

AI-RAN consolidates AI services and Radio Access Network (RAN) functions onto a unified, GPU-accelerated infrastructure at the network edge. However, compute sharing between real-time RAN functions and highly heterogeneous AI services requires coordination of scheduling decisions at mismatched timescales, and placement adaptation may require service migration across nodes with non-negligible interruptions. This paper proposes a hierarchical agentic framework (HAF) for compute sharing in AI-RAN that combines a large language model (LLM)-based agent for slow-timescale placement of AI services and RAN functions with a closed-form, deadline-aware convex algorithm for fast-timescale GPU/CPU allocation. The LLM agent is further equipped with a predictive critic that filters out migrations when the induced service interruption outweighs the expected service-level objective (SLO) benefit. Experimental results show that HAF reaches 90.0% overall SLO fulfillment, a 20.5% improvement over the strongest baseline, and raises AI service request fulfillment from 51% to 85.3%. Further evaluations show that HAF retains its advantage under diverse load conditions, while the critic consistently improves SLO fulfillment across multiple open-source LLM agents.

cs.DC↗

arXiv2026

Multi-Turn Distributed Inference with Mixture of Experts for 6G Edge--Cloud Networks

Mixture-of-Experts (MoE) architectures are increasingly deployed across 6G edge--cloud networks, where sparse activation reduces the computational footprint of each inference to only a fraction of the full expert set. However, MoE inference in edge-cloud networks creates a tension between KV state locality and elastic expert dispatch. KV state relocation incurs substantial transfer overhead, while expert computation benefits from spreading across the network to exploit available capacity. This tension is amplified in multi-turn inference, where each turn extends the KV state that must persist across the dialogue. To this end, we present StateFlow, a distributed inference policy that decouples persistent KV state from transient sparse computation. StateFlow pins KV state at a sticky serving site for cross-turn reuse and jointly optimizes expert dispatch and aggregation placement across the network. We further implement a real-world testbed with kernel-level network emulation and experimental results show that StateFlow sustains more than $2\times$ higher stable dialogue concurrency than the distributed baseline solutions and reduces turn-level p95 latency under multi-turn inference by 53.0\%.

cs.DC↗

arXiv2026

RoboCOIN: An Open-Sourced Bimanual Robotic Data Collection for Integrated Manipulation

Despite the critical role of bimanual manipulation in endowing robots with human-like dexterity, large-scale and diverse datasets remain scarce due to the significant hardware heterogeneity across bimanual robotic platforms. To bridge this gap, we introduce RoboCOIN, a large-scale multi-embodiment bimanual manipulation dataset comprising over 180,000 demonstrations collected from 15 distinct robotic platforms. Spanning 16 diverse environments-including residential, commercial, and industrial settings-the dataset features 421 bimanual tasks systematically categorized by 39 bimanual collaboration actions and 432 objects. A key innovation of our work is the hierarchical capability pyramid, which provides granular annotations ranging from trajectory-level concepts to segment-level subtasks and frame-level kinematics. Furthermore, we present CoRobot, an efficient data processing pipeline powered by the Robot Trajectory Markup Language (RTML), designed to facilitate quality assessment, automated annotation, and unified multi-embodiment and data management. Extensive experiments demonstrate the effectiveness of RoboCOIN in enhancing the performance of various bimanual manipulation models across a wide spectrum of robotic embodiments. The entire dataset and codebase are fully open-sourced, providing a valuable resource for advancing research in bimanual and multi-embodiment manipulation.

cs.RO↗

arXiv2026

Multi-Agentic AI for Conflict-Aware rApp Policy Orchestration in Open RAN

Open Radio Access Network (RAN) enables flexible, AI-driven control of mobile networks through disaggregated, multi-vendor components. In this architecture, xApps handle real-time functions, whereas rApps in the non-real-time controller generate strategic policies. However, current rApp development remains largely manual, brittle, and poorly scalable as xApp diversity proliferates. In this work, we propose a Multi-Agentic AI framework to automate rApp policy generation and orchestration. The architecture integrates three specialized large language model (LLM)-based agents, Perception, Reasoning, and Refinement, supported by retrieval-augmented generation (RAG) and memory-based analogical reasoning. These agents collectively analyze potential conflicts, synthesize intent-aligned control pipelines, and incrementally refine deployment decisions. Experiments across diverse deployment scenarios demonstrate that the proposed system achieves over 70% improvement in deployment accuracy and 95% reduction in reasoning cost compared to baseline methods, while maintaining zero-shot generalization to unseen intents. These results establish a scalable and conflict-aware solution for fully autonomous, zero-touch rApp orchestration in Open RAN.

eess.SY↗

arXiv2026

Multi-Agentic AI for Fairness-Aware and Accelerated Multi-modal Large Model Inference in Real-world Mobile Edge Networks

Generative AI (GenAI) has transformed applications in natural language processing and content creation, yet centralized inference remains hindered by high latency, limited customizability, and privacy concerns. Deploying large models (LMs) in mobile edge networks emerges as a promising solution. However, it also poses new challenges, including heterogeneous multi-modal LMs with diverse resource demands and inference speeds, varied prompt/output modalities that complicate orchestration, and resource-limited infrastructure ill-suited for concurrent LM execution. In response, we propose a Multi-Agentic AI framework for latency- and fairness-aware multi-modal LM inference in mobile edge networks. Our solution includes a long-term planning agent, a short-term prompt scheduling agent, and multiple on-node LM deployment agents, all powered by foundation language models. These agents cooperatively optimize prompt routing and LM deployment through natural language reasoning over runtime telemetry and historical experience. To evaluate its performance, we further develop a city-wide testbed that supports network monitoring, containerized LM deployment, intra-server resource management, and inter-server communications. Experiments demonstrate that our solution reduces average latency by over 80% and improves fairness (Normalized Jain index) to 0.90 compared to other baselines. Moreover, our solution adapts quickly without fine-tuning, offering a generalizable solution for optimizing GenAI services in edge environments.

eess.SY↗

arXiv2025

Incremental DRL-Based Resource Management for Dynamic Network Slicing in an Urban-Wide Testbed

Multi-access edge computing provides localized resources within mobile networks to address the requirements of emerging latency-sensitive and computing-intensive applications. At the edge, dynamic requests necessitate sophisticated resource management for adaptive network slicing. This involves optimizing resource allocations, scaling functions, and load balancing to utilize only essential resources under constrained network scenarios. However, existing solutions largely assume static slice counts, ignoring the re-optimization overhead associated with management algorithms when slices fluctuate. Moreover, many approaches rely on simplified energy models that overlook intertemporal resource scheduling and are predominantly evaluated through simulations, neglecting critical practical considerations. This paper presents an incremental cooperative Multi-Agent Deep Deterministic Policy Gradient (MADDPG) algorithm for resource management in dynamic edge slicing. The proposed approach optimizes long-term slicing benefits by reducing delay and energy consumption while minimizing retraining overhead in response to slice variations. Furthermore, we implement an urban-wide edge computing testbed based on OpenStack and Kubernetes to validate the algorithm's performance. Experimental results demonstrate that our incremental MADDPG method outperforms benchmark strategies in aggregated slicing utility and reduces training energy consumption by up to 50% compared to the re-optimization approach.

eess.SY↗

arXiv2025

Towards Practical Operation of Deep Reinforcement Learning Agents in Real-World Network Management at Open RAN Edges

Deep Reinforcement Learning (DRL) has emerged as a powerful solution for meeting the growing demands for connectivity, reliability, low latency and operational efficiency in advanced networks. However, most research has focused on theoretical analysis and simulations, with limited investigation into real-world deployment. To bridge the gap and support practical DRL deployment for network management, we first present an orchestration framework that integrates ETSI Multi-access Edge Computing (MEC) with Open RAN, enabling seamless adoption of DRL-based strategies across different time scales while enhancing agent lifecycle management. We then identify three critical challenges hindering DRL's real-world deployment, including (1) asynchronous requests from unpredictable or bursty traffic, (2) adaptability and generalization across heterogeneous topologies and evolving service demands, and (3) prolonged convergence and service interruptions due to exploration in live operational environments. To address these challenges, we propose a three-fold solution strategy: (a) advanced time-series integration for handling asynchronized traffic, (b) flexible architecture design such as multi-agent DRL and incremental learning to support heterogeneous scenarios, and (c) simulation-driven deployment with transfer learning to reduce convergence time and service disruptions. Lastly, the feasibility of the MEC-O-RAN architecture is validated on an urban-wide testing infrastructure, and two real-world use cases are presented, showcasing the three identified challenges and demonstrating the effectiveness of the proposed solutions.

cs.NI↗

arXiv2025

Cooperative Task Offloading through Asynchronous Deep Reinforcement Learning in Mobile Edge Computing for Future Networks

Future networks (including 6G) are poised to accelerate the realisation of Internet of Everything. However, it will result in a high demand for computing resources to support new services. Mobile Edge Computing (MEC) is a promising solution, enabling to offload computation-intensive tasks to nearby edge servers from the end-user devices, thereby reducing latency and energy consumption. However, relying solely on a single MEC server for task offloading can lead to uneven resource utilisation and suboptimal performance in complex scenarios. Additionally, traditional task offloading strategies specialise in centralised policy decisions, which unavoidably entail extreme transmission latency and reach computational bottleneck. To fill the gaps, we propose a latency and energy efficient Cooperative Task Offloading framework with Transformer-driven Prediction (CTO-TP), leveraging asynchronous multi-agent deep reinforcement learning to address these challenges. This approach fosters edge-edge cooperation and decreases the synchronous waiting time by performing asynchronous training, optimising task offloading, and resource allocation across distributed networks. The performance evaluation demonstrates that the proposed CTO-TP algorithm reduces up to 80% overall system latency and 87% energy consumption compared to the baseline schemes.

cs.LG↗

arXiv2024

NetMind: Adaptive RAN Baseband Function Placement by GCN Encoding and Maze-solving DRL

The disaggregated and hierarchical architecture of advanced RAN presents significant challenges in efficiently placing baseband functions and user plane functions in conjunction with Multi-Access Edge Computing (MEC) to accommodate diverse 5G services. Therefore, this paper proposes a novel approach NetMind, which leverages Deep Reinforcement Learning (DRL) to determine the function placement strategies in RANs with diverse topologies, aiming at minimizing power consumption. NetMind formulates the function placement problem as a maze-solving task, enabling a Markov Decision Process with standardized action space scales across different networks. Additionally, a Graph Convolutional Network (GCN) based encoding mechanism is introduced, allowing features from different networks to be aggregated into a single RL agent. That facilitates the RL agent's generalization capability and minimizes the negative impact of retraining on power consumption. In an example with three sub-networks, NetMind achieves comparable performance to traditional methods that require a dedicated DRL agent for each network, resulting in a 70% reduction in training costs. Furthermore, it demonstrates a substantial 32.76% improvement in power savings and a 41.67% increase in service stability compared to benchmarks from the existing literature.

cs.NI↗

arXiv2023

DRL-based Energy-Efficient Baseband Function Deployments for Service-Oriented Open RAN

Open Radio Access Network (Open RAN) has gained tremendous attention from industry and academia with decentralized baseband functions across multiple processing units located at different places. However, the ever-expanding scope of RANs, along with fluctuations in resource utilization across different locations and timeframes, necessitates the implementation of robust function management policies to minimize network energy consumption. Most recently developed strategies neglected the activation time and the required energy for the server activation process, while this process could offset the potential energy savings gained from server hibernation. Furthermore, user plane functions, which can be deployed on edge computing servers to provide low-latency services, have not been sufficiently considered. In this paper, a multi-agent deep reinforcement learning (DRL) based function deployment algorithm, coupled with a heuristic method, has been developed to minimize energy consumption while fulfilling multiple requests and adhering to latency and resource constraints. In an 8-MEC network, the DRL-based solution approaches the performance of the benchmark while offering up to 51% energy savings compared to existing approaches. In a larger network of 14-MEC, it maintains a 38% energy-saving advantage and ensures real-time response capabilities. Furthermore, this paper prototypes an Open RAN testbed to verify the feasibility of the proposed solution.

cs.NI↗