arXiv subjects

Xiaoyi Fan

Publications and source records attributed to Xiaoyi Fan.

At least 19 recordsLinked to original sources

arXiv2026

Can AI Agents Detect and Repair Artifact Drift in Network Experiments?

In recent years, AI agents have evolved into capable assistants that carry out multi-step tasks in digital environments. The network systems community is beginning to explore these capabilities in operational and experimental settings. However, an agent operating in network systems should not be judged solely by whether it completes the immediate task. The experiment record it modifies must also remain trustworthy. We call this property artifact integrity: the record's claims must remain supported by the available evidence, confined to the scope established by that evidence, and traceable through the artifacts that encode their support. To make this property measurable, we introduce NetArtifactBench, which tests whether AI agents can repair inconsistent records derived from public network-system artifacts while preserving claims that remain supported. The benchmark contains 52 instances with injected inconsistencies ranging from direct contradictions to unstated relations spread across several artifacts. We evaluate 23 agent configurations across three general-purpose AI agent runtimes using deterministic scoring. The average contract pass rate is 65.3 % across 5,980 outputs, but no agent runtime exceeds 30 % when repair requires recovering implicit relations and propagating changes across artifacts. These results reveal a sharp boundary between local correction and complete record-level repair. Therefore, we argue that artifact integrity should become a first-class design and evaluation requirement for AI agents operating on network systems.

cs.NI↗

arXiv2026

TrapVLA: Trapping Vision-Language-Action Models in Configured Failure Modes

This work introduces Configured Failure Trapping, a novel backdoor attack task against Vision-Language-Action (VLA) models, which aims to activate attacks through stealthy textual triggers and induce configured failure modes. Unlike prior backdoor attacks that treat any task failure as a successful attack, Configured Failure Trapping requires the attacker to control how the robot fails (e.g., causing the robot to grasp with a specified positional offset), making it substantially more challenging and hard to detect. To support the new task, we propose an effective data engine for synthesizing high-quality target trajectories and an automated suite for measuring configured-failure fidelity. Then, based on this foundation, we construct two new benchmarks, namely Trap-LIBERO and Trap-RoboTwin, that instantiate Configured Failure Trapping across four representative failure modes. To address this task, we identify sparse action deviation as a critical challenge and accordingly propose a novel method named TrapVLA, which explicitly learns trigger-induced action residuals to steer the policy toward the configured failure behavior. Extensive experiments across simulation benchmarks and real-world robotic settings show that TrapVLA effectively injects configured failure modes into VLA models while largely preserving performance on clean data. Project page: https://john-liua.github.io/TrapVLA/

cs.RO↗

arXiv2026

DynamicManip: Enabling Dynamic Manipulation from a Single Static Demonstration

Dynamic manipulation is a critical capability for robots operating in complex and dynamic environments, where robots must interact with objects that are moving or require rapid adjustments. However, learning models for dynamic manipulation tasks face two major challenges: (1) the combinatorial complexity of dynamic scenarios leads to substantial data requirements, and (2) rapid variations in dynamics require real-time and accurate policy execution. In this paper, we propose DynamicManip to address these challenges through an efficient data augmentation pipeline and a low-latency imitation policy. We first propose a static-to-dynamic augmentation pipeline that synthesizes diverse dynamic manipulation demonstrations from a single static demonstration. Second, we introduce a dynamic-aware adaptive policy that adjusts its inference frequency according to task dynamics, enabling responsive and effective dynamic manipulation. Third, we build a dynamic manipulation benchmark, which includes diverse dynamic tasks with an automatic evaluation system for scalable and consistent assessment. Extensive experiments in both simulation and the real world demonstrate that DynamicManip not only provides significant improvements in data efficiency but also achieves better performance in dynamic manipulation tasks, with a mean success rate 18.4 percentage points higher and policy-query latency 32.9% lower.

cs.RO↗

arXiv2026

From Tokens to Energy Flexibility: Quantization-Enabled Demand Response for Data Centers with LLM Inference Workloads

The rapid growth of large language model (LLM) inference is creating significant data-center loads that face increasing energy-management challenges under tightening grid conditions and demand response (DR) requirements. Conventional data-center energy management mainly relies on temporal and spatial workload shifting and campus-level energy asset scheduling, but it usually treats LLM inference demand as an aggregate load. As a result, these approaches fail to exploit the internal characteristics of LLM serving and therefore overlook the flexibility offered by LLM-specific techniques such as model quantization. To unlock this flexibility, this paper proposes a quantization-enabled energy management framework for grid-responsive LLM inference data centers. First, a quantization-to-power model is established to map each model--quantization configuration to a compact set of dispatchable parameters. Second, a two-stage quantization-enabled DR model is developed to account for model instance switching, request routing, and precision selection. Third, a multi-campus co-optimization method is introduced for DR participation by integrating grid-side electricity and carbon signals with the quantization-enabled DR model. Case studies show that the proposed framework reduces total data-center operating cost by 34.3\% without curtailing served token volume, validating model quantization as an effective flexibility lever for grid-responsive LLM data-center energy management.

eess.SY↗

arXiv2026

Hera: Learning Long-Horizon Coordination for Device-Cloud Collaborative LLM Agents

Large language model (LLM) agents excel at solving complex long-horizon tasks through autonomous interaction with environments. However, their real-world deployment faces a fundamental device--cloud dilemma: on-device models are efficient but often brittle, while cloud models are stronger but costly in computation. State-of-the-art LLM device--cloud routers usually make coarse task-level decisions, which cannot adapt to the changing difficulty of multi-step agent interactions. To address this issue, we present Hera, a step-level device--cloud LLM agent coordinator for long-horizon tasks achieving a strong performance--cost Pareto frontier. Hera adopts a novel two-stage training paradigm: (1) imitation learning for cold-start, followed by (2) reinforcement learning that jointly optimizes task success and cloud usage efficiency. The first stage casts step-level routing as a supervised classification problem: the device agent is replayed on cloud trajectories, with each state labeled by the agreement between device and cloud actions. In the second stage, we perform cost-aware reinforcement learning by grouping identical states across trajectories and updating Hera with labels favoring higher expected return and fewer future cloud calls. We evaluate Hera on ALFWorld, WebShop, and AppWorld, where it consistently outperforms prior methods, achieving 92.5% of the cloud-only success rate with cloud use in only 46.3% of steps.

cs.AI↗

arXiv2026

DyGRO-VLA: Cross-Task Scaling of Vision-Language-Action Models via Dynamic Grouped Residual Optimization

Recent progress in Reinforcement Learning (RL) provides a principled approach to optimizing Vision-Language-Action (VLA) models, facilitating a shift from trajectory imitation to active learning in the task environment. Despite improvements in control precision, most RL optimizers remain task-specific, which reduces VLA models from generalist controllers to policies that overfit to a narrow set of tasks. In this study, we conduct an in-depth analysis of this phenomenon and highlight the importance of cross-task feature representations for improving the generalizability of VLA models. Motivated by this finding, we introduce DyGRO-VLA, a two-stage optimization framework that 1) effectively captures cross-task latent representations based on information-theoretic principles, and 2) dynamically refines policy optimization via a mixture-of-RL-residuals. DyGRO-VLA enables the RL optimizer to exploit task-relevant latent information while strategically mitigating adverse interference on the learned representations throughout the optimization process. We evaluate our approach on LIBERO, RoboTwin2 benchmarks, and further validate it on real world, demonstrating consistent improvements over strong baselines under multi-task training and distribution shift.

cs.RO↗

arXiv2026

GoodServe: Towards High-Goodput Serving of Agentic LLM Inferences over Heterogeneous Resources

Large Language Models (LLMs) play a critical role in emerging agentic applications, where the timely completion of each entire inference is critical. Meanwhile, agentic LLM inferences are increasingly served on heterogeneous GPUs in operator's resource pools. Therefore, it is crucial to route incoming inference requests to appropriate GPUs so that their end-to-end latency requirements are satisfied whenever possible, thereby achieving high goodput. In this paper, we propose GoodServe, a goodput-optimized serving system for agentic inferences over heterogeneous resources. GoodServe performs inference routing in a predict-and-rectify manner. It estimates the request output lengths as well as the GPU serving status in an accurate and also practical manner. Based on information from both the demand and resource sides, it then makes high-quality routing decisions using a just-enough instance selection heuristic. It also periodically monitors SLO-violation risks of active requests and triggers runtime request migrations to address unexpected dynamics. Our evaluations show that GoodServe improves goodput by up to 27.4% over existing routing methods.

cs.DC↗

arXiv2026

SensingAgents: A Multi-Agent Collaborative Framework for Robust IMU Activity Recognition

Human Activity Recognition (HAR) using Inertial Measurement Unit (IMU) sensors is a cornerstone of mobile health, smart environments, and human-computer interaction. However, current deep learning-based HAR models often struggle with heavy reliance on labeled data, position-specific ambiguity, and a lack of transparent reasoning. Inspired by the advanced agents framework, which emulates a collaborative agent using Large Language Models (LLMs), we propose SensingAgents, a novel multi-agent system for robust IMU activity recognition. SensingAgents organizes LLM-powered agents into specialized roles: a group of Analyst Agents for position-specific sensor analysis (arm, wrist, belt, pocket), a pair of Advocate Agents that resolves sensor conflicts through dynamic and static dialectical debates, and a Decision Agent that ensures reliability under sensor drift or failure. Evaluation on the Shoaib dataset demonstrates that SensingAgents significantly outperforms state-of-the-art single-agent and multi-agent LLM models, achieving an accuracy of 79.5% in a zero setting--29% higher than existing agent models and 9.4% higher than deep learning baselines--particularly in complex scenarios where multi-sensor data is conflicting or noisy. Our work highlights the potential of multi-agent collaborative reasoning for advancing the robustness and interpretability of ubiquitous sensing systems.

cs.AI↗

arXiv2026

Renewables Power the Orbit? Achieving Sustainable Space Edge Computing via QoS-Aware Offloading

Low-Earth-Orbit (LEO) satellite constellations are becoming integral to 6G infrastructure, but increasing in-orbit computation accelerates battery degradation and raises sustainability concerns. Meanwhile, renewable-heavy regions worldwide experience persistent energy curtailment due to transmission bottlenecks, leaving substantial clean energy stranded near generation sites. We identify a satellite-grid co-design opportunity: adaptively offloading task-critical data from satellite to data centers co-located with renewable power plants. However, realizing this vision requires jointly considering intermittent and capacity-limited communication windows, as well as time-varying electricity budgets. In this paper, we propose SQSO, a Sustainable and QoS-aware Satellite Offloading framework that models per-interval task offloading as a constrained optimization over dynamic topology and electricity prices. Under this framework, we design $\text{AO}^2$, an adaptive offloading orchestration algorithm to solve the formulated optimization problem. Using Starlink-scale simulations and real-world electricity price traces, $\text{AO}^2$ reduces energy consumption by up to 76.03% and battery life consumption by up to 76.85% compared to state-of-the-art schemes, while also lowering task delay. This work highlights that sustainable scaling of LEO constellations requires co-design of space networking and renewable energy infrastructure, while our solution promotes renewable-aware task offloading and cross-domain collaboration for space-energy integration in the 6G era.

cs.NI↗

arXiv2026

MesonGS++: Post-training Compression of 3D Gaussian Splatting with Hyperparameter Searching

3D Gaussian Splatting (3DGS) achieves high-quality novel view synthesis with real-time rendering, but its storage cost remains prohibitive for practical deployment. Existing post-training compression methods still rely on many coupled hyperparameters across pruning, transformation, quantization, and entropy coding, making it difficult to control the final compressed size and fully exploit the rate-distortion trade-off. We propose MesonGS++, a size-aware post-training codec for 3D Gaussian compression. On the codec side, MesonGS++ combines joint importance-based pruning, octree geometry coding, attribute transformation, selective vector quantization for higher-degree spherical harmonics, and group-wise mixed-precision quantization with entropy coding. On the configuration side, it treats the reserve ratio and bit-width allocation as the dominant rate-distortion knobs and jointly optimizes them under a target storage budget via discrete sampling and 0--1 integer linear programming. We further propose a linear size estimator and a CUDA parallel quantization operator to accelerate the hyperparameter searching process. Extensive experiments show that MesonGS++ achieves over 34$\times$ compression while preserving rendering fidelity, outperforming state-of-the-art post-training methods and accurately meeting target size budgets. Remarkably, without any training, MesonGS++ can even surpass the PSNR of vanilla 3DGS at a 20$\times$ compression rate on the Stump scene. Our code is available at https://github.com/mmlab-sigs/mesongs_plus

cs.CV↗

arXiv2026

Rethink Web Service Resilience in Space: A Radiation-Aware and Sustainable Transmission Solution

Low Earth Orbit (LEO) satellite networks such as Starlink and Project Kuiper are increasingly integrated with cloud infrastructures, forming an important internet backbone for global web services. By extending connectivity to remote regions, oceans, and disaster zones, these networks enable reliable access to applications ranging from real-time WebRTC communication to emergency response portals. Yet the resilience of these web services is threatened by space radiation: it degrades hardware, drains batteries, and disrupts continuity, even if the space-cloud integrated providers use machine learning to analyze space weather and radiation data. Specifically, conventional fixes like altitude adjustments and thermal annealing consume energy; neglecting this energy use results in deep discharge and faster battery aging, whereas sleep modes risk abrupt web session interruptions. Efficient network-layer mitigation remains a critical gap. We propose RALT (Radiation-Aware LEO Transmission), a control-plane solution that dynamically reroutes traffic during radiation events, accounting for energy constraints to minimize battery degradation and sustain service performance. Our work shows that unlocking space-based web services' full potential for global reliable connectivity requires rethinking resilience through the lens of the space environment itself.

cs.MM↗

arXiv2026

S-HPLB: Efficient LLM Attention Serving via Sparsity-Aware Head Parallelism Load Balance

With the increasing volumes of Large Language Models (LLMs) and the expanding context lengths, attention computation has become a key performance bottleneck in LLM serving. For fast attention computation, recent practices often parallelize the attention heads on multiple GPUs, and also widely adopt attention sparsification to reduce the computation amount -- which selectively computes a subset of attention pairs under a preset sparsity budget. In this paper, we notice that attention heads of an LLM model often exhibit heterogeneous-yet-stable sparsity elasticities, which motivates us to enforce head-adaptive sparsity budgets to attain better efficiency while preserving high inference quality. Yet, from the system aspect, with heterogeneous sparsity levels, attention computation time on different heads would be inconsistent, yielding cross-GPU resource bubbles under head-parallel deployment. To further minimize such bubbles, we propose a novel attention deployment strategy called Sparsity-aware Head-Parallel Load Balance (S-HPLB). Experiments on long-context benchmark show that, S-HPLB can achieve a $2.88\times$ improvement in average attention computation latency without quality degradation.

cs.DC↗

arXiv2025

A Nesterov-Accelerated Byzantine-Robust Federated Learning

We investigate robust federated learning, where a group of workers collaboratively train a shared model under the orchestration of a central server in the presence of Byzantine adversaries capable of arbitrary and potentially malicious behaviors. To simultaneously enhance communication efficiency and resilience against such adversaries, we propose a Byzantine-resilient Nesterov-accelerated federated learning (Byrd-NAFL) algorithm. Byrd-NAFL seamlessly integrates Nesterov's momentum into the federated learning process alongside Byzantine-resilient aggregation rules to achieve fast and safe convergence against gradient corruption. We establish a finite-time convergence guarantee for Byrd-NAFL under non-convex and smooth loss functions with relaxed assumptions on the aggregated gradients. Extensive numerical experiments validate the effectiveness of Byrd-NAFL and demonstrate the superiority over existing benchmarks in terms of convergence speed, accuracy, and resilience to diverse malicious attacks.

cs.LG↗

arXiv2025

CO-PFL: Contribution-Oriented Personalized Federated Learning for Heterogeneous Networks

Personalized federated learning (PFL) addresses a critical challenge of collaboratively training customized models for clients with heterogeneous and scarce local data. Conventional federated learning, which relies on a single consensus model, proves inadequate under such data heterogeneity. Its standard aggregation method of weighting client updates heuristically or by data volume, operates under an equal-contribution assumption, failing to account for the actual utility and reliability of each client's update. This often results in suboptimal personalization and aggregation bias. To overcome these limitations, we introduce Contribution-Oriented PFL (CO-PFL), a novel algorithm that dynamically estimates each client's contribution for global aggregation. CO-PFL performs a joint assessment by analyzing both gradient direction discrepancies and prediction deviations, leveraging information from gradient and data subspaces. This dual-subspace analysis provides a principled and discriminative aggregation weight for each client, emphasizing high-quality updates. Furthermore, to bolster personalization adaptability and optimization stability, CO-PFL cohesively integrates a parameter-wise personalization mechanism with mask-aware momentum optimization. Our approach effectively mitigates aggregation bias, strengthens global coordination, and enhances local performance by facilitating the construction of tailored submodels with stable updates. Extensive experiments on four benchmark datasets (CIFAR10, CIFAR10C, CINIC10, and Mini-ImageNet) confirm that CO-PFL consistently surpasses state-of-the-art methods in in personalization accuracy, robustness, scalability and convergence stability.

cs.LG↗

arXiv2025

Exploring and Mitigating Fawning Hallucinations in Large Language Models

Large language models (LLMs) have demonstrated exceptional proficiency in language understanding. However, when LLMs align their outputs with deceptive and/or misleading prompts, the generated responses could deviate from the de facto information. Such observations are known as fawning hallucinations, where the model prioritizes alignment with the input's implied perspective over accuracy and truthfulness. In this work, we analyze fawning hallucinations in various natural language processing tasks and tailor the so-termed contrastive decoding method for fawning-hallucination mitigation. Specifically, we design two paradigms to generate corresponding deceptive and/or misleading inputs for the consistent fawning hallucinations induction. Then, we propose the collaborative contrastive decoding (CCD) to handle the fawning hallucinations across different tasks in LLMs. By contrasting the deviation in output distribution between induced and transformed neutral inputs, the proposed CCD can reduce reliance on deceptive and/or misleading information without requiring additional training. Extensive experiments demonstrate that the proposed CCD can effectively mitigate fawning hallucinations and improve the factuality of the generated responses over various tasks.

cs.CL↗

arXiv2025

Towards Integrated Energy-Communication-Transportation Hub: A Base-Station-Centric Design in 5G and Beyond

The rise of 5G communication has transformed the telecom industry for critical applications. With the widespread deployment of 5G base stations comes a significant concern about energy consumption. Key industrial players have recently shown strong interest in incorporating energy storage systems to store excess energy during off-peak hours, reducing costs and participating in demand response. The fast development of batteries opens up new possibilities, such as the transportation area. An effective method is needed to maximize base station battery utilization and reduce operating costs. In this trend towards next-generation smart and integrated energy-communication-transportation (ECT) infrastructure, base stations are believed to play a key role as service hubs. By exploring the overlap between base station distribution and electric vehicle charging infrastructure, we demonstrate the feasibility of efficiently charging EVs using base station batteries and renewable power plants at the Hub. Our model considers various factors, including base station traffic conditions, weather, and EV charging behavior. This paper introduces an incentive mechanism for setting charging prices and employs a deep reinforcement learning-based method for battery scheduling. Experimental results demonstrate the effectiveness of our proposed ECT-Hub in optimizing surplus energy utilization and reducing operating costs, particularly through revenue-generating EV charging.

cs.NI↗

arXiv2025

Model Splitting Enhanced Communication-Efficient Federated Learning for CSI Feedback

Recent advancements have introduced federated machine learning-based channel state information (CSI) compression before the user equipments (UEs) upload the downlink CSI to the base transceiver station (BTS). However, most existing algorithms impose a high communication overhead due to frequent parameter exchanges between UEs and BTS. In this work, we propose a model splitting approach with a shared model at the BTS and multiple local models at the UEs to reduce communication overhead. Moreover, we implant a pipeline module at the BTS to reduce training time. By limiting exchanges of boundary parameters during forward and backward passes, our algorithm can significantly reduce the exchanged parameters over the benchmarks during federated CSI feedback training.

eess.SP↗

arXiv2025

LLMSched: Uncertainty-Aware Workload Scheduling for Compound LLM Applications

Developing compound Large Language Model (LLM) applications is becoming an increasingly prevalent approach to solving real-world problems. In these applications, an LLM collaborates with various external modules, including APIs and even other LLMs, to realize complex intelligent services. However, we reveal that the intrinsic duration and structural uncertainty in compound LLM applications pose great challenges for LLM service providers in serving and scheduling them efficiently. In this paper, we propose LLMSched, an uncertainty-aware scheduling framework for emerging compound LLM applications. In LLMSched, we first design a novel DAG-based model to describe the uncertain compound LLM applications. Then, we adopt the Bayesian network to comprehensively profile compound LLM applications and identify uncertainty-reducing stages, along with an entropy-based mechanism to quantify their uncertainty reduction. Combining an uncertainty reduction strategy and a job completion time (JCT)-efficient scheme, we further propose an efficient scheduler to reduce the average JCT. Evaluation of both simulation and testbed experiments on various representative compound LLM applications shows that compared to existing state-of-the-art scheduling schemes, LLMSched can reduce the average JCT by 14~79%.

cs.DC↗