Searcharxiv⌕ Search

arXiv subjects

Yong Cui

Publications and source records attributed to Yong Cui.

At least 19 recordsLinked to original sources
arXiv2026

NetConfArena: An Executable Benchmark for LLM Agents in Closed-Loop Network Configuration

Large language model (LLM) agents are increasingly attractive for automating network configuration, yet their reliability and failure patterns are poorly understood. An essential prerequisite is to assess such agents in a realistic but risk-free environment. Existing benchmarks, however, fall short: they often treat configuration as static command generation or rely on overly simplified settings. Such evaluations understate the core challenges of network configuration, where correctness requires reasoning about protocol complexity and topology dependence. We present NetConfArena, an executable benchmark for evaluating LLM agents in closed-loop network configuration. NetConfArena places agents in emulated multi-device networks, provides a standardized and compact action interface for task execution, and evaluates the resulting network behavior with hidden task-specific executable test cases. The benchmark relies on an LLM-assisted, emulation-grounded pipeline, which converts human-oriented network materials into reusable parameterized task templates. We evaluate representative LLM agents on 480 task instances instantiated from 96 protocol-focused task templates, yielding 3840 execution trajectories, and show that failures are not limited to command errors. The failures also reveal gaps in task-specification adherence and robust planning and execution. These findings suggest two future directions: using validated trajectories as supervision signals to improve foundation models, and designing harness mechanisms that make agent execution more reliable and accountable.

cs.NI↗
arXiv2026

UniAlign: A Model-Agnostic Framework for Robust Network Traffic Classification under Distribution Shifts

Network traffic classification (NTC) models often suffer severe performance degradation when deployed in real-world environments due to distribution shifts caused by changing network conditions. Existing robustness-enhancing approaches are commonly coupled to specific model architectures or data settings, fail to generalize to state-of-the-art raw-byte-based NTC models, or incur significant training overhead. In this paper, we propose UniAlign, a novel model-agnostic framework that improves the robustness of deep learning-based NTC models under distribution shifts. UniAlign combines \emph{domain alignment fine-tuning}, which encourages the learning of domain-invariant traffic representations across heterogeneous network conditions, with \emph{stable model ensembling}, which enhances inference robustness by aggregating checkpoints within a flat loss region. The framework can be seamlessly integrated into existing supervised NTC models without requiring specific feature modalities or introducing non-constant additional training costs. We evaluate UniAlign on three public datasets covering diverse distribution shifts, including encryption schemes, data collection devices, and attack behaviors. Experimental results on two representative NTC models demonstrate that, compared with standard training, UniAlign improves average classification accuracy by 2.51\% and average F1 score by 2.71\%, outperforming the strongest baseline by 1.45\% in accuracy and 1.69\% in F1 score, while requiring only 12.4\%--53.9\% of the training time of all NTC-specific baselines.

cs.LG↗
arXiv2026

Embedded Model Predictive Control for EMS-type Maglev Vehicles

Current developments of high-speed magnetic levitation technology using the principle of the electromagnet suspension (EMS) focus on reaching vehicle speeds of more than 600 km/h. With increasing vehicle speeds, however, updated control algorithms need to be investigated to reliably stabilize the system and meet the demands in terms of ride comfort. This article examines the modern and popular approach of model predictive control and its application to the magnetic levitation control system. Investigated key aspects are the parameterization of the model predictive controller and its implementation on embedded, resource constrained hardware. The results reveal that model predictive control is capable to robustly stabilize the highly nonlinear and constrained system even at very high speed. Furthermore, processor-in-the-loop studies are carried out to validate the designed control algorithms on a microcontroller.

eess.SY↗
arXiv2026

PEMI: Transparent Performance Enhancements for QUIC

QUIC, as the transport layer of the next-generation Web stack (HTTP/3), natively provides security and performance improvements over TCP-based stacks. However, since QUIC provides end-to-end encryption for both data and packet headers, in-network assistance like Performance-Enhancing Proxy (PEP) is unavailable for QUIC. To achieve the similar optimization as TCP, some works seek to collaborate endpoints and middleboxes to provide in-network assistance for QUIC. But involving both host and in-network devices increases the difficulty of deployment in the Internet. In this paper, by analyzing the QUIC standard, implementations, and the locality of application traffic, we identify opportunities for transparent middleboxes to measure RTT and infer packet loss for QUIC connections, despite the absence of plaintext ACK information. We then propose PEMI as a concrete system that continuously measures RTT and infers lost packets, enabling fast retransmissions for QUIC. PEMI enables performance enhancement for QUIC in a completely transparent manner, without requiring any explicit cooperation from the endpoints. To keep fairness, PEMI employs a delay-based congestion control and utilizes feedback-based methods to enforce CWND. Extensive evaluation results, including Mininet and trace-driven dynamic experiments, show that PEMI can significantly improve the performance of QUIC. For example, in the Mininet experiments, PEMI increases the goodput of file transfers by up to 2.5$\times$, and reduces the 90th percentile jitter of RTC frames by 20-75%.

cs.NI↗
arXiv2026

NetMamba+: A Framework of Pre-trained Models for Efficient and Accurate Network Traffic Classification

With the rapid growth of encrypted network traffic, effective traffic classification has become essential for network security and quality of service management. Current machine learning and deep learning approaches for traffic classification face three critical challenges: computational inefficiency of Transformer architectures, inadequate traffic representations with loss of crucial byte-level features while retaining detrimental biases, and poor handling of long-tail distributions in real-world data. We propose NetMamba+, a framework that addresses these challenges through three key innovations: (1) an efficient architecture considering Mamba and Flash Attention mechanisms, (2) a multimodal traffic representation scheme that preserves essential traffic information while eliminating biases, and (3) a label distribution-aware fine-tuning strategy. Evaluation experiments on massive datasets encompassing four main classification tasks showcase NetMamba+'s superior classification performance compared to state-of-the-art baselines, with improvements of up to 6.44\% in F1 score. Moreover, NetMamba+ demonstrates excellent efficiency, achieving 1.7x higher inference throughput than the best baseline while maintaining comparably low memory usage. Furthermore, NetMamba+ exhibits superior few-shot learning abilities, achieving better classification performance with fewer labeled data. Additionally, we implement an online traffic classification system that demonstrates robust real-world performance with a throughput of 261.87 Mb/s. As the first framework to adapt Mamba architecture for network traffic classification, NetMamba+ opens new possibilities for efficient and accurate traffic analysis in complex network environments.

cs.LG↗
arXiv2026

Bias in the Shadows: Explore Shortcuts in Encrypted Network Traffic Classification

Pre-trained models operating directly on raw bytes have achieved promising performance in encrypted network traffic classification (NTC), but often suffer from shortcut learning-relying on spurious correlations that fail to generalize to real-world data. Existing solutions heavily rely on model-specific interpretation techniques, which lack adaptability and generality across different model architectures and deployment scenarios. In this paper, we propose BiasSeeker, the first semi-automated framework that is both model-agnostic and data-driven for detecting dataset-specific shortcut features in encrypted traffic. By performing statistical correlation analysis directly on raw binary traffic, BiasSeeker identifies spurious or environment-entangled features that may compromise generalization, independent of any classifier. To address the diverse nature of shortcut features, we introduce a systematic categorization and apply category-specific validation strategies that reduce bias while preserving meaningful information. We evaluate BiasSeeker on 19 public datasets across three NTC tasks. By emphasizing context-aware feature selection and dataset-specific diagnosis, BiasSeeker offers a novel perspective for understanding and addressing shortcut learning in encrypted network traffic classification, raising awareness that feature selection should be an intentional and scenario-sensitive step prior to model training.

cs.LG↗
arXiv2025

Automated Network Protocol Testing with LLM Agents

Network protocol testing is fundamental for modern network infrastructure. However, traditional network protocol testing methods are labor-intensive and error-prone, requiring manual interpretation of specifications, test case design, and translation into executable artifacts, typically demanding one person-day of effort per test case. Existing model-based approaches provide partial automation but still involve substantial manual modeling and expert intervention, leading to high costs and limited adaptability to diverse and evolving protocols. In this paper, we propose a first-of-its-kind system called NeTestLLM that takes advantage of multi-agent Large Language Models (LLMs) for end-to-end automated network protocol testing. NeTestLLM employs hierarchical protocol understanding to capture complex specifications, iterative test case generation to improve coverage, a task-specific workflow for executable artifact generation, and runtime feedback analysis for debugging and refinement. NeTestLLM has been deployed in a production environment for several months, receiving positive feedback from domain experts. In experiments, NeTestLLM generated 4,632 test cases for OSPF, RIP, and BGP, covering 41 historical FRRouting bugs compared to 11 by current national standards. The process of generating executable artifacts also improves testing efficiency by a factor of 8.65x compared to manual methods. NeTestLLM provides the first practical LLM-powered solution for automated end-to-end testing of heterogeneous network protocols.

cs.NI↗
arXiv2025

LEED: A Highly Efficient and Scalable LLM-Empowered Expert Demonstrations Framework for Multi-Agent Reinforcement Learning

Multi-agent reinforcement learning (MARL) holds substantial promise for intelligent decision-making in complex environments. However, it suffers from a coordination and scalability bottleneck as the number of agents increases. To address these issues, we propose the LLM-empowered expert demonstrations framework for multi-agent reinforcement learning (LEED). LEED consists of two components: a demonstration generation (DG) module and a policy optimization (PO) module. Specifically, the DG module leverages large language models to generate instructions for interacting with the environment, thereby producing high-quality demonstrations. The PO module adopts a decentralized training paradigm, where each agent utilizes the generated demonstrations to construct an expert policy loss, which is then integrated with its own policy loss. This enables each agent to effectively personalize and optimize its local policy based on both expert knowledge and individual experience. Experimental results show that LEED achieves superior sample efficiency, time efficiency, and robust scalability compared to state-of-the-art baselines.

cs.MA↗
arXiv2025

Sample Efficient Experience Replay in Non-stationary Environments

Reinforcement learning (RL) in non-stationary environments is challenging, as changing dynamics and rewards quickly make past experiences outdated. Traditional experience replay (ER) methods, especially those using TD-error prioritization, struggle to distinguish between changes caused by the agent's policy and those from the environment, resulting in inefficient learning under dynamic conditions. To address this challenge, we propose the Discrepancy of Environment Dynamics (DoE), a metric that isolates the effects of environment shifts on value functions. Building on this, we introduce Discrepancy of Environment Prioritized Experience Replay (DEER), an adaptive ER framework that prioritizes transitions based on both policy updates and environmental changes. DEER uses a binary classifier to detect environment changes and applies distinct prioritization strategies before and after each shift, enabling more sample-efficient learning. Experiments on four non-stationary benchmarks demonstrate that DEER further improves the performance of off-policy algorithms by 11.54 percent compared to the best-performing state-of-the-art ER methods.

cs.LG↗
arXiv2025

AI Agent Communication from Internet Architecture Perspective: Challenges and Opportunities

The rapid development of AI agents leads to a surge in communication demands. Alongside this rise, a variety of frameworks and protocols emerge. While these efforts demonstrate the vitality of the field, they also highlight increasing fragmentation, with redundant innovation and siloed designs hindering cross-domain interoperability. These challenges underscore the need for a systematic perspective to guide the development of scalable, secure, and sustainable AI agent ecosystems. To address this need, this paper provides the first systematic analysis of AI agent communication from the standpoint of Internet architecture-the most successful global-scale distributed system in history. Specifically, we distill decades of Internet evolution into five key elements that are directly relevant to agent communication: scalability, security, real-time performance, high performance, and manageability. We then use these elements to examine both the opportunities and the bottlenecks in developing robust multi-agent ecosystems. Overall, this paper bridges Internet architecture and AI agent communication for the first time, providing a new lens for guiding the sustainable growth of AI agent communication ecosystems.

cs.NI↗
arXiv2025

KeepKV: Achieving Periodic Lossless KV Cache Compression for Efficient LLM Inference

Efficient inference of large language models (LLMs) is hindered by an ever-growing key-value (KV) cache, making KV cache compression a critical research direction. Traditional methods selectively evict less important KV cache entries, which leads to information loss and hallucinations. Recently, merging-based strategies have been explored to retain more information by merging KV pairs that would be discarded; however, these existing approaches inevitably introduce inconsistencies in attention distributions before and after merging, causing degraded generation quality. To overcome this challenge, we propose KeepKV, a novel adaptive KV cache merging method designed to preserve performance under strict memory constraints, achieving single-step lossless compression and providing error bounds for multi-step compression. KeepKV introduces the Electoral Votes mechanism that records merging history and adaptively adjusts attention scores. Moreover, it further leverages a novel Zero Inference-Perturbation Merging method, compensating for attention loss resulting from cache merging. Extensive experiments on various benchmarks and LLM architectures demonstrate that KeepKV substantially reduces memory usage while successfully retaining essential context information, achieving over 2x inference throughput improvement and maintaining superior generation quality even with only 10% KV cache budgets.

cs.LG↗
arXiv2025

Klyachko vector bundles over topological toric manifolds

We give a Klyachko-type classification of topological/smooth/holomorphic $(\mathbb{C}^{*})^n$-equivariant vector bundles that are equivariantly trivial over invariant affine charts. This generalizes Klyachko's classification of toric vector bundles.

math.AG↗
arXiv2025

State-Aware Perturbation Optimization for Robust Deep Reinforcement Learning

Recently, deep reinforcement learning (DRL) has emerged as a promising approach for robotic control. However, the deployment of DRL in real-world robots is hindered by its sensitivity to environmental perturbations. While existing whitebox adversarial attacks rely on local gradient information and apply uniform perturbations across all states to evaluate DRL robustness, they fail to account for temporal dynamics and state-specific vulnerabilities. To combat the above challenge, we first conduct a theoretical analysis of white-box attacks in DRL by establishing the adversarial victim-dynamics Markov decision process (AVD-MDP), to derive the necessary and sufficient conditions for a successful attack. Based on this, we propose a selective state-aware reinforcement adversarial attack method, named STAR, to optimize perturbation stealthiness and state visitation dispersion. STAR first employs a soft mask-based state-targeting mechanism to minimize redundant perturbations, enhancing stealthiness and attack effectiveness. Then, it incorporates an information-theoretic optimization objective to maximize mutual information between perturbations, environmental states, and victim actions, ensuring a dispersed state-visitation distribution that steers the victim agent into vulnerable states for maximum return reduction. Extensive experiments demonstrate that STAR outperforms state-of-the-art benchmarks.

cs.LG↗
arXiv2025

Robust Deep Reinforcement Learning in Robotics via Adaptive Gradient-Masked Adversarial Attacks

Deep reinforcement learning (DRL) has emerged as a promising approach for robotic control, but its realworld deployment remains challenging due to its vulnerability to environmental perturbations. Existing white-box adversarial attack methods, adapted from supervised learning, fail to effectively target DRL agents as they overlook temporal dynamics and indiscriminately perturb all state dimensions, limiting their impact on long-term rewards. To address these challenges, we propose the Adaptive Gradient-Masked Reinforcement (AGMR) Attack, a white-box attack method that combines DRL with a gradient-based soft masking mechanism to dynamically identify critical state dimensions and optimize adversarial policies. AGMR selectively allocates perturbations to the most impactful state features and incorporates a dynamic adjustment mechanism to balance exploration and exploitation during training. Extensive experiments demonstrate that AGMR outperforms state-of-the-art adversarial attack methods in degrading the performance of the victim agent and enhances the victim agent's robustness through adversarial defense mechanisms.

cs.LG↗
arXiv2025

LLM-Sketch: Enhancing Network Sketches with LLM

Network stream mining is fundamental to many network operations. Sketches, as compact data structures that offer low memory overhead with bounded accuracy, have emerged as a promising solution for network stream mining. Recent studies attempt to optimize sketches using machine learning; however, these approaches face the challenges of lacking adaptivity to dynamic networks and incurring high training costs. In this paper, we propose LLM-Sketch, based on the insight that fields beyond the flow IDs in packet headers can also help infer flow sizes. By using a two-tier data structure and separately recording large and small flows, LLM-Sketch improves accuracy while minimizing memory usage. Furthermore, it leverages fine-tuned large language models (LLMs) to reliably estimate flow sizes. We evaluate LLM-Sketch on three representative tasks, and the results demonstrate that LLM-Sketch outperforms state-of-the-art methods by achieving a $7.5\times$ accuracy improvement.

cs.NI↗
arXiv2025

INTA: Intent-Based Translation for Network Configuration with LLM Agents

Translating configurations between different network devices is a common yet challenging task in modern network operations. This challenge arises in typical scenarios such as replacing obsolete hardware and adapting configurations to emerging paradigms like Software Defined Networking (SDN) and Network Function Virtualization (NFV). Engineers need to thoroughly understand both source and target configuration models, which requires considerable effort due to the complexity and evolving nature of these specifications. To promote automation in network configuration translation, we propose INTA, an intent-based translation framework that leverages Large Language Model (LLM) agents. The key idea of INTA is to use configuration intent as an intermediate representation for translation. It first employs LLMs to decompose configuration files and extract fine-grained intents for each configuration fragment. These intents are then used to retrieve relevant manuals of the target device. Guided by a syntax checker, INTA incrementally generates target configurations. The translated configurations are further verified and refined for semantic consistency. We implement INTA and evaluate it on real-world configuration datasets from the industry. Our approach outperforms state-of-the-art methods in translation accuracy and exhibits strong generalizability. INTA achieves an accuracy of 98.15% in terms of both syntactic and view correctness, and a command recall rate of 84.72% for the target configuration. The semantic consistency report of the translated configuration further demonstrates its practical value in real-world network operations.

cs.NI↗
arXiv2025

Rethinking Adversarial Attacks in Reinforcement Learning from Policy Distribution Perspective

Deep Reinforcement Learning (DRL) suffers from uncertainties and inaccuracies in the observation signal in realworld applications. Adversarial attack is an effective method for evaluating the robustness of DRL agents. However, existing attack methods targeting individual sampled actions have limited impacts on the overall policy distribution, particularly in continuous action spaces. To address these limitations, we propose the Distribution-Aware Projected Gradient Descent attack (DAPGD). DAPGD uses distribution similarity as the gradient perturbation input to attack the policy network, which leverages the entire policy distribution rather than relying on individual samples. We utilize the Bhattacharyya distance in DAPGD to measure policy similarity, enabling sensitive detection of subtle but critical differences between probability distributions. Our experiment results demonstrate that DAPGD achieves SOTA results compared to the baselines in three robot navigation tasks, achieving an average 22.03% higher reward drop compared to the best baseline.

cs.LG↗