arXiv subjects

Qiao Xiang

Publications and source records attributed to Qiao Xiang.

18 recordsLinked to original sources

arXiv2026

LLM-as-a-Judge for Reliable and Explainable Offline Evaluation in Top-K Recommendation

Recommendation evaluation plays a crucial role in guiding the refinement and deployment of recommender systems. Most existing trials rely on offline evaluation using Top-K metrics computed over holdout user behaviors. However, we identify two fundamental limitations that undermine their ability to deliver reliable and explainable evaluations. Regarding reliability, offline evaluation treats observed user feedback as a proxy of true preferences and enforces rigid ID matching between the proxy and recommendation. In practice, feedback collections are inherently shaped by incomplete and biased item exposure, leading to distorted and unreliable assessments. Regarding explainability, Top-K metrics only establish numerical scores without offering meaningful insights to support them, thereby reinforcing the black-box nature of offline evaluation. In this paper, we propose a reliable and explainable LLM-as-a-Judge framework for offline recommendation evaluation. To enhance reliability, we introduce a semantic proxy from user textual behaviors to represent their true preferences. This proxy allows for more flexible matching between preferences and recommendations in the semantic space, rather than depending on the holdout feedback. To ensure explainability, the LLM Judge adopts a reasoning-then-scoring process to generate relevance judgments along with explicit rationale. Finally, we aggregate the individual scores into global Top-K metrics to quantify overall recommendation quality, and provide justification for each preference hit or miss. Extensive experiments demonstrate that the LLM Judge achieves solid reliability, explainability, and robustness in evaluation.

cs.IR↗

arXiv2026

AGZO: Activation-Guided Zeroth-Order Optimization for LLM Fine-Tuning

Zeroth-Order (ZO) optimization has emerged as a promising solution for fine-tuning LLMs under strict memory constraints, as it avoids the prohibitive memory cost of storing activations for backpropagation. However, existing ZO methods typically employ isotropic perturbations, neglecting the rich structural information available during the forward pass. In this paper, we identify a crucial link between gradient formation and activation structure: the gradient of a linear layer is confined to the subspace spanned by its input activations. Leveraging this insight, we propose Activation-Guided Zeroth-Order optimization (AGZO). Unlike prior methods, AGZO extracts a compact, activation-informed subspace on the fly during the forward pass and restricts perturbations to this low-rank subspace. We provide a theoretical framework showing that AGZO optimizes a subspace-smoothed objective and provably yields update directions with higher cosine similarity to the true gradient than isotropic baselines. Empirically, we evaluate AGZO on Qwen3 and Pangu models across various benchmarks. AGZO consistently outperforms state-of-the-art ZO baselines and significantly narrows the performance gap with first-order fine-tuning, while maintaining almost the same peak memory footprint as other ZO methods.

cs.LG↗

arXiv2026

Unleashing the Power of Tree-of-Thoughts for Edge-Enabled AIGC Service Provisioning

Delivering AI-generated content (AIGC) services fundamentally relies on the reasoning capabilities of generative AI (GenAI) models. Chain-of-Thought (CoT) enhances such reasoning by guiding models through intermediate steps, while Tree-of-Thoughts (ToT) further extends CoT by exploring multiple candidate reasoning paths simultaneously, thereby greatly improving AIGC service quality. However, generating diverse reasoning paths requires separate calls to computationally intensive GenAI models, posing significant challenges for resource constrained user devices. In this paper, we investigate mobile edge computing-enabled AIGC service provisioning with ToT prompting. Specifically, using creative writing AIGC tasks as a case study, we first characterize the number of output tokens as a measure of computational resources in GenAI models and establish its relationship with generation delay and quality through experiments with Qwen 2.5-7B-Instruct. Afterward, we introduce a directed acyclic graph (DAG) model to accurately characterize the reasoning process of ToT prompting, where each vertex represents a thought and each directed edge denotes a transition between consecutive thoughts. We then formulate a DAG-based thought assignment problem aimed at minimizing generation delay subject to a user-adjustable quality constraint. To address this problem, we propose a diffusion-based soft actor-critic (DSAC) algorithm that innovatively integrates diffusion models to determine optimal thought assignment decisions. Through extensive simulations, we demonstrate that the proposed DSAC achieves total generation delay reductions of up to 8.32% over PPO, 11.57% over SAC, and 36.09% over DDQN across various simulation settings, while reducing latency by over 80% compared to the fully local generation baseline even under stringent quality requirements.

cs.DC↗

arXiv2026

Innovation Discovery System for Networking Research

As networking systems become increasingly complex, achieving disruptive innovation grows more challenging. At the same time, recent progress in Large Language Models (LLMs) has shown strong potential for scientific hypothesis formation and idea generation. Nevertheless, applying LLMs effectively to networking research remains difficult for two main reasons: standalone LLMs tend to generate ideas by recombining existing solutions, and current open-source networking resources do not provide the structured, idea-level knowledge necessary for data-driven scientific discovery. To bridge this gap, we present SciNet, a research idea generation system specifically designed for networking. SciNet is built upon three key components: (1) constructing a networking-oriented scientific discovery dataset from top-tier networking conferences, (2) simulating the human idea discovery workflow through problem setting, inspiration retrieval, and idea generation, and (3) developing an idea evaluation method that jointly measures novelty and practicality. Experimental results show that \system consistently produces practical and novel networking research ideas across multiple LLM backbones, and outperforms standalone LLM-based generation in overall idea quality.

cs.NI↗

arXiv2026

A Systematic Evaluation of On-Device LLMs: Quantization, Performance, and Resources

Deploying Large Language Models (LLMs) on edge devices enhances privacy but faces performance hurdles due to limited resources. We introduce a systematic methodology to evaluate on-device LLMs, balancing capability, efficiency, and resource constraints. Through an extensive analysis of models (0.5B-14B) and seven post-training quantization (PTQ) methods on commodity hardware, we demonstrate that: 1) Heavily quantized large models consistently outperform smaller, high-precision models, with a performance threshold at ~3.5 effective bits-per-weight (BPW); 2) Resource utilization scales linearly with BPW, though power and memory footprints vary by quantization algorithm; and 3) With a reduction in model size, the primary constraint on throughput transitions from communication overhead to computational latency. We conclude by offering guidelines for optimizing LLMs in resource-constrained edge environments. Our codebase is available at https://anonymous.4open.science/r/LLMOnDevice/.

cs.LG↗

arXiv2026

Diagnosing and Repairing Distributed Routing Configurations Using Selective Symbolic Simulation

Although substantial progress has been made in automatically verifying whether distributed routing configurations conform to certain requirements, diagnosing and repairing configuration errors remains manual and time-consuming. To fill this gap, we propose S^2Sim, a novel system for automatic routing configuration diagnosis and repair. Our key insight is that by selectively simulating variants of the given configuration in a symbolic way, we can find an intent-compliant variant, whose differences between the given configuration reveal the errors in the given configuration and suggest the patches. Building on this insight, we also design techniques to support complex scenarios (e.g., multiple protocol networks) and requirements (e.g., k-link failure tolerance). We implement a prototype of S^2Sim and evaluate its performance using networks of size O(10) ~ O(1000) with synthetic real-world configurations. Results show that S^2Sim diagnoses and repairs errors for 1) all WAN configurations within 10 s and 2) all DCN configurations within 20 minutes.

cs.NI↗

arXiv2026

Holmes: An Evidence-Grounded LLM Agent for Auditable DDoS Investigation in Cloud Networks

Cloud environments face frequent DDoS threats due to centralized resources and broad attack surfaces. Modern cloud-native DDoS attacks further evolve rapidly and often blend multi-vector strategies, creating an operational dilemma: defenders need wire-speed monitoring while also requiring explainable, auditable attribution for response. Existing rule-based and supervised-learning approaches typically output black-box scores or labels, provide limited evidence chains, and generalize poorly to unseen attack variants; meanwhile, high-quality labeled data is often difficult to obtain in cloud settings. We present Holmes (DDoS Detective), an LLM-based DDoS detection agent that reframes the model as a virtual SRE investigator rather than an end-to-end classifier. Holmes couples a funnel-like hierarchical workflow (counters/sFlow for continuous sensing and triage; PCAP evidence collection triggered only on anomaly windows) with an Evidence Pack abstraction that converts binary packets into compact, reproducible, high-signal structured evidence. On top of this evidence interface, Holmes enforces a structure-first investigation protocol and strict JSON/quotation constraints to produce machine-consumable reports with auditable evidence anchors. We evaluate Holmes on CICDDoS2019 reflection/amplification attacks and script-triggered flooding scenarios. Results show that Holmes produces attribution decisions grounded in salient evidence anchors across diverse attack families, and when errors occur, its audit logs make the failure source easy to localize, demonstrating the practicality of an LLM agent for cost-controlled and traceable DDoS investigation in cloud operations.

cs.CR↗

arXiv2025

Argo: An efficient verification framework for distributed in-network computing

Distributed in-network programs are increasingly deployed in data centers for their performance benefits, but shifting application logic to switches also enlarges the failure domain. Ensuring their correctness before deployment is thus critical for reliability. While prior verification frameworks can efficiently detect bugs for programs running on a single switch, they overlook the common interactive behaviors in distributed settings, thereby missing related bugs that can cause state inconsistencies and system failures. This paper presents Procurator, a verification framework that efficiently captures interactive behaviors in distributed in-network programs. Procurator introduces a formal model combining the actor paradigm with Communicating Sequential Processes (CSP), translating pipeline execution into reactive, event-driven actors and unifying their interactions as message passing. To support flexible specification of distributed properties, it provides a unified intent language. Additionally, it incorporates a semantic-aware state pruner to reduce verification complexity, thus ensuring system scalability. Evaluation results show that Procurator efficiently uncovers 10 distinct bugs caused by interactive behaviors across five real-world in-network systems. It also reduces verification time by up to 913.2x and memory consumption by up to 1.9x compared to the state-of-the-art verifier.

cs.NI↗

arXiv2025

Janus: Leveraging Incremental Computation for Efficient DNS Verification

Existing DNS configuration verification tools face significant issues (e.g., inefficient and lacking support for incremental verification). Inspired by the advancements in recent work of distributed data plane verification and the resemblance be- tween the data plane and DNS configuration, we tackle the challenge of DNS misconfiguration by introducing Janus, a DNS verification tool. Our key insight is that the process of a nameserver handling queries can be transformed into a matching process on a match-action table. With this insight, Janus consists of (1) an efficient data structure for partition query space based on the behaviors, (2) a symbolic execution algorithm that specifies how a single nameserver can efficiently cover all possible queries and ensure the accuracy of verification, (3) a mechanism to support incremental verification with less computational effort. Extensive experiments on real-world datasets (with over 6 million resource records) show that Janus achieves significant speedups, with peak improvements of up to 255.7x and a maximum 6046x reduction in the number of LECs.

cs.NI↗

arXiv2025

RepLLM: Toward Automatically Reproducing Network Research Results

Result reproduction of computer networking research is challenging as the scarcity of open-source implementations and the complexity of heterogeneous system architectures. Even though Large Language Models have demonstrated potential in code generation, existing code generation frameworks often fail to address the long-context constraints and intricate logical dependencies, which are vital in reproducing network systems from academic papers. Thus, we introduce RepLLM, an end-to-end multi-agent framework designed to automate code reproduction from paper content. RepLLM features a collaborative architecture comprising four specialized agents -- Content Parsing, Architecture Design, Code Generation, and Audit&Repair, which are coordinated through Shared Memory mechanism to ensure global context consistency. With the enhancement of Structured Chain-of-Thought LLM reasoning and a sandbox-isolated static-dynamic debugging methodology, our framework effectively resolves semantic discrepancies and runtime errors, thereby improving reliable reproductions. Extensive evaluations on representative papers in top conferences demonstrate that RepLLM outperforms state-of-the-art system-level LLM frameworks in generating compile-ready and logically correct systems. Our results show that, with the aid of RepLLM, we can reproduce 95% of the original benchmarks within approximately two hours while reducing token consumption by up to 10% compared with state-of-the-art baselines.

cs.NI↗

arXiv2023

Toward Reproducing Network Research Results Using Large Language Models

Reproducing research results in the networking community is important for both academia and industry. The current best practice typically resorts to three approaches: (1) looking for publicly available prototypes; (2) contacting the authors to get a private prototype; and (3) manually implementing a prototype following the description of the publication. However, most published network research does not have public prototypes and private prototypes are hard to get. As such, most reproducing efforts are spent on manual implementation based on the publications, which is both time and labor consuming and error-prone. In this paper, we boldly propose reproducing network research results using the emerging large language models (LLMs). In particular, we first prove its feasibility with a small-scale experiment, in which four students with essential networking knowledge each reproduces a different networking system published in prominent conferences and journals by prompt engineering ChatGPT. We report the experiment's observations and lessons and discuss future open research questions of this proposal. This work raises no ethical issue.

cs.LG↗

arXiv2023

From RDMA to RDCA: Toward High-Speed Last Mile of Data Center Networks Using Remote Direct Cache Access

In this paper, we conduct systematic measurement studies to show that the high memory bandwidth consumption of modern distributed applications can lead to a significant drop of network throughput and a large increase of tail latency in high-speed RDMA networks.We identify its root cause as the high contention of memory bandwidth between application processes and network processes. This contention leads to frequent packet drops at the NIC of receiving hosts, which triggers the congestion control mechanism of the network and eventually results in network performance degradation. To tackle this problem, we make a key observation that given the distributed storage service, the vast majority of data it receives from the network will be eventually written to high-speed storage media (e.g., SSD) by CPU. As such, we propose to bypass host memory when processing received data to completely circumvent this performance bottleneck. In particular, we design Lamda, a novel receiver cache processing system that consumes a small amount of CPU cache to process received data from the network at line rate. We implement a prototype of Lamda and evaluate its performance extensively in a Clos-based testbed. Results show that for distributed storage applications, Lamda improves network throughput by 4.7% with zero memory bandwidth consumption on storage nodes, and improves network throughput by up 17% and 45% for large block size and small size under the memory bandwidth pressure, respectively. Lamda can also be applied to latency-sensitive HPC applications, which reduces their communication latency by 35.1%.

cs.NI↗

arXiv2022

Switch as a Verifier: Toward Scalable Data Plane Checking via Distributed, On-Device Verification

Data plane verification (DPV) is important for finding network errors. Current DPV tools employ a centralized architecture, where a server collects the data planes of all devices and verifies them. Despite substantial efforts on accelerating DPV, this centralized architecture is inherently unscalable. In this paper, to tackle the scalability challenge of DPV, we circumvent the scalability bottleneck of centralized design and design Coral, a distributed, on-device DPV framework. The key insight of Coral is that DPV can be transformed into a counting problem on a directed acyclic graph, which can be naturally decomposed into lightweight tasks executed at network devices, enabling scalability. Coral consists of (1) a declarative requirement specification language, (2) a planner that employs a novel data structure DVNet to systematically decompose global verification into on-device counting tasks, and (3) a distributed verification (DV) protocol that specifies how on-device verifiers communicate task results efficiently to collaboratively verify the requirements. We implement a prototype of Coral. Extensive experiments with real-world datasets (WAN/LAN/DC) show that Coral consistently achieves scalable DPV under various networks and DPV scenarios, i.e., up to 1250 times speed up in the scenario of burst update, and up to 202 times speed up on 80% quantile of incremental verification, than state-of-the-art DPV tools, with little overhead on commodity network devices.

eess.SY↗

arXiv2022

Achieving Efficient Distributed Machine Learning Using a Novel Non-Linear Class of Aggregation Functions

Distributed machine learning (DML) over time-varying networks can be an enabler for emerging decentralized ML applications such as autonomous driving and drone fleeting. However, the commonly used weighted arithmetic mean model aggregation function in existing DML systems can result in high model loss, low model accuracy, and slow convergence speed over time-varying networks. To address this issue, in this paper, we propose a novel non-linear class of model aggregation functions to achieve efficient DML over time-varying networks. Instead of taking a linear aggregation of neighboring models as most existing studies do, our mechanism uses a nonlinear aggregation, a weighted power-p mean (WPM), as the aggregation function of local models from neighbors. The subsequent optimizing steps are taken using mirror descent defined by a Bregman divergence that maintains convergence to optimality. In this paper, we analyze properties of the WPM and rigorously prove convergence properties of our aggregation mechanism. Additionally, through extensive experiments, we show that when p > 1, our design significantly improves the convergence speed of the model and the scalability of DML under time-varying networks compared with arithmetic mean aggregation functions, with little additional computation overhead.

cs.LG↗

arXiv2022

IVeri: Privacy-Preserving Interdomain Verification

In an interdomain network, autonomous systems (ASes) often establish peering agreements, so that one AS (agreement consumer) can influence the routing policies of the other AS (agreement provider). Peering agreements are implemented in the BGP configuration of the agreement provider. It is crucial to verify their implementation because one error can lead to disastrous consequences. However, the fundamental challenge for peering agreement verification is how to preserve the privacy of both ASes involved in the agreement. To this end, this paper presents IVeri, the first privacy-preserving interdomain agreement verification system. IVeri models the interdomain agreement verification problem as a SAT formula, and develops a novel, efficient, privacy-serving SAT solver, which uses oblivious shuffling and garbled circuits as the key building blocks to let the agreement consumer and provider collaboratively verify the implementation of interdomain peering agreements without exposing their private information. A prototype of IVeri is implemented and evaluated extensively. Results show that IVeri achieves accurate, privacy-preserving interdomain agreement verification with reasonable overhead.

cs.CR↗

arXiv2022

Carbide: Highly Reliable Networks Through Real-Time Multiple Control Plane Composition

Achieving highly reliable networks is essential for network operators to ensure proper packet delivery in the event of software errors or hardware failures. Networks must ensure reachability and routing correctness, such as subnet isolation and waypoint traversal. Existing work in network verification relies on centralized computation at the cost of fault tolerance, while other approaches either build an over-engineered, complex control plane, or compose multiple control planes without providing any guarantee on correctness. This paper presents Carbide, a novel system to achieve high reliability in networks through distributed verification and multiple control plane composition. The core of Carbide is a simple, generic, efficient distributed verification framework that transforms a generic network verification problem to a reachability verification problem on a directed acyclic graph (DAG), and solves the latter via an efficient distributed verification protocol (DV-protocol). Equipped with verification results, Carbide allows the systematic composition of multiple control planes and realization of operator-specified consistency. Carbide is fully implemented. Extensive experiments show that (1) Carbide reduces downtime by 43% over the most reliable individual underlying control plane, while enforcing correctness requirements on all traffic; and (2) by systematically decomposing computation to devices and pruning unnecessary messaging between devices during verification, Carbide scales to a production data center network.

cs.NI↗

arXiv2021

Vulcan: Solving the Steiner Tree Problem with Graph Neural Networks and Deep Reinforcement Learning

Steiner Tree Problem (STP) in graphs aims to find a tree of minimum weight in the graph that connects a given set of vertices. It is a classic NP-hard combinatorial optimization problem and has many real-world applications (e.g., VLSI chip design, transportation network planning and wireless sensor networks). Many exact and approximate algorithms have been developed for STP, but they suffer from high computational complexity and weak worst-case solution guarantees, respectively. Heuristic algorithms are also developed. However, each of them requires application domain knowledge to design and is only suitable for specific scenarios. Motivated by the recently reported observation that instances of the same NP-hard combinatorial problem may maintain the same or similar combinatorial structure but mainly differ in their data, we investigate the feasibility and benefits of applying machine learning techniques to solving STP. To this end, we design a novel model Vulcan based on novel graph neural networks and deep reinforcement learning. The core of Vulcan is a novel, compact graph embedding that transforms highdimensional graph structure data (i.e., path-changed information) into a low-dimensional vector representation. Given an STP instance, Vulcan uses this embedding to encode its pathrelated information and sends the encoded graph to a deep reinforcement learning component based on a double deep Q network (DDQN) to find solutions. In addition to STP, Vulcan can also find solutions to a wide range of NP-hard problems (e.g., SAT, MVC and X3C) by reducing them to STP. We implement a prototype of Vulcan and demonstrate its efficacy and efficiency with extensive experiments using real-world and synthetic datasets.

cs.LG↗

arXiv2021

Toward Efficient Federated Learning in Multi-Channeled Mobile Edge Network with Layerd Gradient Compression

A fundamental issue for federated learning (FL) is how to achieve optimal model performance under highly dynamic communication environments. This issue can be alleviated by the fact that modern edge devices usually can connect to the edge FL server via multiple communication channels (e.g., 4G, LTE and 5G). However, having an edge device send copies of local models to the FL server along multiple channels is redundant, time-consuming, and would waste resources (e.g., bandwidth, battery life and monetary cost). In this paper, motivated by the layered coding techniques in video streaming, we propose a novel FL framework called layered gradient compression (LGC). Specifically, in LGC, local gradients from a device is coded into several layers and each layer is sent to the FL server along a different channel. The FL server aggregates the received layers of local gradients from devices to update the global model, and sends the result back to the devices. We prove the convergence of LGC, and formally define the problem of resource-efficient federated learning with LGC. We then propose a learning based algorithm for each device to dynamically adjust its local computation (i.e., the number of local stochastic descent) and communication decisions (i.e.,the compression level of different layers and the layer to channel mapping) in each iteration. Results from extensive experiments show that using our algorithm, LGC significantly reduces the training time, improves the resource utilization, while achieving a similar accuracy, compared with well-known FL mechanisms.

cs.LG↗