arXiv subjects

Minghe Wang

Publications and source records attributed to Minghe Wang.

8 recordsLinked to original sources

arXiv2026

SkillTrace: Multi-Trace Provenance Auditing for LLM-Agent Skill Reuse

LLM-agent ecosystems are rapidly growing around reusable skills: mixed-modality packages of metadata, natural-language instructions, code, tools, references, and operational workflows. As skills become marketplace artifacts, auditing their reuse is no longer the same problem as ordinary code clone detection. Existing detectors target single-modality source code or whole-package similarity, yet skill reuse evidence is distributed across authored text, implementation fragments, and operational structure. As a result, they can miss reuse that preserves only one part of a skill. We present SKILLTRACE, a multi-trace provenance auditing framework for LLM-agent skill reuse. SKILLTRACE extracts three provenance traces: Expression, Implementation, and Operational. It represents the Operational Trace as a Skill Operational Graph (SOG) that captures activation, procedure, and resource-flow structure. An LLM assists only the Operational-trace extraction, once at ingestion; at audit time SKILLTRACE compares cached traces deterministically, calibrates each trace against same-function strict negatives, and reports which trace supports a reuse decision. On SKILLTRACE-BENCH, with 820 transformed reuse positives over 100 marketplace anchors and 751 negative controls, SKILLTRACE achieves AUROC 0.938 and F1 0.898. A 36,446-skill wild audit further shows that trace-attributed evidence surfaces actionable reuse review queues beyond repository-level baselines.

cs.AI↗

arXiv2026

FaaSMoE: A Serverless Framework for Multi-Tenant Mixture-of-Experts Serving

Mixture-of-Experts (MoE) models offer high capacity with efficient inference cost by activating a small subset of expert models per input. However, deploying MoE models requires all experts to reside in memory, creating a gap between the resource used by activated experts and the provisioned resources. This underutilization is further pronounced in multi-tenant scenarios. In this paper, we propose FaaSMoE, a multi-tenant MoE serving architecture built on Function-as-a-Service (FaaS) platforms. FaaSMoE decouples the control and execution planes of MoE by deploying experts as stateless FaaS functions, enabling on-demand and scale-to-zero expert invocation across tenants. FaaSMoE further supports configurable expert granularity within functions, trading off per-expert elasticity for reduced invocation overhead. We implement a prototype with an open-source edge-oriented FaaS platform and evaluate it using Qwen1.5-moe-2.7B under multi-tenant workloads. Compared to a full-model baseline, FaaSMoE uses less than one third of the resources, demonstrating a practical and resource-efficient path towards scalable MoE serving in a multi-tenant environment.

cs.DC↗

arXiv2025

DisCEdge: Distributed Context Management for Large Language Models at the Edge

Deploying Large Language Model (LLM) services at the edge benefits latency-sensitive and privacy-aware applications. However, the stateless nature of LLMs makes managing user context (e.g., sessions, preferences) across geo-distributed edge nodes challenging. Existing solutions, such as client-side context storage, introduce network latency and bandwidth overhead, undermining edge deployment advantages. We propose DisCEdge, a distributed context management system that stores and replicates user context in tokenized form across edge nodes. By maintaining context as token sequences, our system avoids redundant computation and enables efficient data replication. We evaluate an open-source prototype in a realistic edge environment. DisCEdge improves median response times by up to 14.46% and lowers median inter-node synchronization overhead by up to 15% compared to a raw-text-based system. It also reduces client request sizes by a median of 90% compared to client-side context management, while guaranteeing data consistency.

cs.DC↗

arXiv2025

Exploring Influence Factors on LLM Suitability for No-Code Development of End User IoT Applications

No-Code Development Platforms (NCDPs) empower non-technical end users to build applications tailored to their specific demands without writing code. While NCDPs lower technical barriers, users still require some technical knowledge, e.g., to structure process steps or define event-action rules. Large Language Models (LLMs) offer a promising solution to further reduce technical requirements by supporting natural language interaction and dynamic code generation. By integrating LLM, NCDPs can be more accessible to non-technical users, enabling application development truly without requiring any technical expertise. Despite growing interest in LLM-powered NCDPs, a systematic investigation into the factors influencing LLM suitability and performance remains absent. Understanding these factors is critical to effectively leveraging LLMs capabilities and maximizing their impact. In this paper, we investigate key factors influencing the effectiveness of LLMs in supporting end-user application development within NCDPs. By conducting comprehensive experiments, we evaluate the impact of four key factors, i.e., model selection, prompt language, training data background, and an error-informed few-shot setup, on the quality of generated applications. Specifically, we selected a range of LLMs based on their architecture, scale, design focus, and training data, and evaluated them across four real-world smart home automation scenarios implemented on a representative open-source LLM-powered NCDP. Our findings offer practical insights into how LLMs can be effectively integrated into NCDPs, informing both platform design and the selection of suitable LLMs for end-user application development.

cs.DC↗

arXiv2025

A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment

The remarkable success of Large Language Models (LLMs) has illuminated a promising pathway toward achieving Artificial General Intelligence for both academic and industrial communities, owing to their unprecedented performance across various applications. As LLMs continue to gain prominence in both research and commercial domains, their security and safety implications have become a growing concern, not only for researchers and corporations but also for every nation. Currently, existing surveys on LLM safety primarily focus on specific stages of the LLM lifecycle, e.g., deployment phase or fine-tuning phase, lacking a comprehensive understanding of the entire "lifechain" of LLMs. To address this gap, this paper introduces, for the first time, the concept of "full-stack" safety to systematically consider safety issues throughout the entire process of LLM training, deployment, and eventual commercialization. Compared to the off-the-shelf LLM safety surveys, our work demonstrates several distinctive advantages: (I) Comprehensive Perspective. We define the complete LLM lifecycle as encompassing data preparation, pre-training, post-training, deployment and final commercialization. To our knowledge, this represents the first safety survey to encompass the entire lifecycle of LLMs. (II) Extensive Literature Support. Our research is grounded in an exhaustive review of over 800+ papers, ensuring comprehensive coverage and systematic organization of security issues within a more holistic understanding. (III) Unique Insights. Through systematic literature analysis, we have developed reliable roadmaps and perspectives for each chapter. Our work identifies promising research directions, including safety in data generation, alignment techniques, model editing, and LLM-based agent systems. These insights provide valuable guidance for researchers pursuing future work in this field.

cs.CR↗

arXiv2025

LLM4FaaS: No-Code Application Development using LLMs and FaaS

Large language models (LLMs) show great capabilities in generating code from natural language descriptions, bringing programming power closer to non-technical users. However, their lack of expertise in operating the generated code remains a key barrier to realizing customized applications. Function-as-a-Service (FaaS) platforms offer a high level of abstraction for code execution and deployment, allowing users to run LLM-generated code without requiring technical expertise or incurring operational overhead. In this paper, we present LLM4FaaS, a no-code application development approach that integrates LLMs and FaaS platforms to enable non-technical users to build and run customized applications using only natural language. By deploying LLM-generated code through FaaS, LLM4FaaS abstracts away infrastructure management and boilerplate code generation. We implement a proof-of-concept prototype based on an open-source FaaS platform, and evaluate it using real prompts from non-technical users. Experiments with GPT-4o show that LLM4FaaS can automatically build and deploy code in 71.47% of cases, outperforming a non-FaaS baseline at 43.48% and an existing LLM-based platform at 14.55%, narrowing the gap to human performance at 88.99%. Further analysis of code quality, programming language diversity, latency, and consistency demonstrates a balanced performance in terms of efficiency, maintainability and availability.

cs.SE↗

arXiv2023

Supporting UAVs with Edge Computing: A Review of Opportunities and Challenges

Over the last years, Unmanned Aerial Vehicles (UAVs) have seen significant advancements in sensor capabilities and computational abilities, allowing for efficient autonomous navigation and visual tracking applications. However, the demand for computationally complex tasks has increased faster than advances in battery technology. This opens up possibilities for improvements using edge computing. In edge computing, edge servers can achieve lower latency responses compared to traditional cloud servers through strategic geographic deployments. Furthermore, these servers can maintain superior computational performance compared to UAVs, as they are not limited by battery constraints. Combining these technologies by aiding UAVs with edge servers, research finds measurable improvements in task completion speed, energy efficiency, and reliability across multiple applications and industries. This systematic literature review aims to analyze the current state of research and collect, select, and extract the key areas where UAV activities can be supported and improved through edge computing.

cs.DC↗

arXiv2023

Lotus: Serverless In-Transit Data Processing for Edge-based Pub/Sub

Publish-subscribe systems are a popular approach for edge-based IoT use cases: Heterogeneous, constrained edge devices can be integrated easily, with message routing logic offloaded to edge message brokers. Message processing, however, is still done on constrained edge devices. Complex content-based filtering, the transformation between data representations, or message extraction place a considerable load on these systems, and resulting superfluous message transfers strain the network. In this paper, we propose Lotus, adding in-transit data processing to an edge publish-subscribe middleware in order to offload basic message processing from edge devices to brokers. Specifically, we leverage the Function-as-a-Service paradigm, which offers support for efficient multi-tenancy, scale-to-zero, and real-time processing. With a proof-of-concept prototype of Lotus, we validate its feasibility and demonstrate how it can be used to offload sensor data transformation to the publish-subscribe messaging middleware.

cs.DC↗