arXiv subjects

Rujia Wang

Publications and source records attributed to Rujia Wang.

At least 19 recordsLinked to original sources

arXiv2026

A Holistic Framework for Automated Configuration Recommendation for Cloud Service Monitoring

Reliability of large-scale cloud services is critical for user satisfaction and business continuity. Despite significant investments in reliability engineering, production incidents remain inevitable, often leading to customer impact and operational overhead. In large cloud companies, multiple services are deployed across regions necessitating robust health monitoring systems. However, the current monitor configuration process is manual, largely reactive and ad hoc, resulting in gaps in coverage and redundant alerts. In this paper, we present a comprehensive study of monitor creation in Microsoft, identifying key components in the existing process. We further design a modular recommendation framework that processes the graph structured service entities to suggest optimal monitor configurations. Through extensive experimentation on historical data and user study of recommendations for production services at Microsoft, we demonstrate the efficacy of our approach in providing relevant recommendations for monitor configurations.

cs.DC↗

arXiv2026

Memora: A Harmonic Memory Representation Balancing Abstraction and Specificity

Agent memory systems must accommodate continuously growing information while supporting efficient, context-aware retrieval for downstream tasks. Abstraction is essential for scaling agent memory, yet it often comes at the cost of specificity, obscuring the fine-grained details required for effective reasoning. We introduce Memora, a harmonic memory representation that structurally balances abstraction and specificity. Memora organizes information via its primary abstractions that index concrete memory values and consolidate related updates into unified memory entries, while cue anchors expand retrieval access across diverse aspects of the memory and connect related memories. Building on this structure, we employ a retrieval policy that actively exploits these memory connections to retrieve relevant information beyond direct semantic similarity. Theoretically, we show that standard Retrieval-Augmented Generation (RAG) and Knowledge Graph (KG)-based memory systems emerge as special cases of our framework. Empirically, Memora establishes a new state-of-the-art on the LoCoMo and LongMemEval benchmarks, demonstrating better retrieval relevance and reasoning effectiveness as memory scales.

cs.AI↗

arXiv2025

ExoAtom: A Database of Atomic Spectra in ExoMol Format

We present the ExoAtom database, www.exomol.com/exoatom, an extension of the ExoMol database to provide atomic line lists in the ExoMol format. ExoAtom is designed for detailed astrophysical, planetary, and laboratory applications. ExoAtom currently includes atomic data for 80 neutral atoms and 74 singly charged ions. These data are extracted from both the NIST and Kurucz databases, with 79/71 atoms/ions sourced from NIST and 38/37 atoms/ions sourced from Kurucz. ExoAtom uses the file types .all, .def, .states, .trans and .pf as fundamental components for structuring atomic data in a consistent hierarchy. The .states file contains quantum numbers, uncertainties, lifetimes, etc. The .trans file specifies Einstein A coefficients and their associated wavenumbers. The .pf file provides partition functions over a wide grid of temperatures. Post-processing of the ExoAtom data is provided by the program PyExoCross. Future development of ExoAtom will include additional ionization stages.

physics.atom-ph↗

arXiv2025

SynthAgent: Adapting Web Agents with Synthetic Supervision

Web agents struggle to adapt to new websites due to the scarcity of environment specific tasks and demonstrations. Recent works have explored synthetic data generation to address this challenge, however, they suffer from data quality issues where synthesized tasks contain hallucinations that cannot be executed, and collected trajectories are noisy with redundant or misaligned actions. In this paper, we propose SynthAgent, a fully synthetic supervision framework that aims at improving synthetic data quality via dual refinement of both tasks and trajectories. Our approach begins by synthesizing diverse tasks through categorized exploration of web elements, ensuring efficient coverage of the target environment. During trajectory collection, tasks are refined only when conflicts with observations are detected, which mitigates hallucinations while preserving task consistency. After collection, we conduct trajectory refinement with global context to mitigate potential noise or misalignments. Finally, we fine-tune open-source web agents on the refined synthetic data to adapt them to the target environment. Experimental results demonstrate that SynthAgent outperforms existing synthetic data methods, validating the importance of high-quality synthetic supervision. The code is publicly available at https://github.com/aiming-lab/SynthAgent.

cs.LG↗

arXiv2025

Attention Enhanced Entity Recommendation for Intelligent Monitoring in Cloud Systems

In this paper, we present DiRecGNN, an attention-enhanced entity recommendation framework for monitoring cloud services at Microsoft. We provide insights on the usefulness of this feature as perceived by the cloud service owners and lessons learned from deployment. Specifically, we introduce the problem of recommending the optimal subset of attributes (dimensions) that should be tracked by an automated watchdog (monitor) for cloud services. To begin, we construct the monitor heterogeneous graph at production-scale. The interaction dynamics of these entities are often characterized by limited structural and engagement information, resulting in inferior performance of state-of-the-art approaches. Moreover, traditional methods fail to capture the dependencies between entities spanning a long range due to their homophilic nature. Therefore, we propose an attention-enhanced entity ranking model inspired by transformer architectures. Our model utilizes a multi-head attention mechanism to focus on heterogeneous neighbors and their attributes, and further attends to paths sampled using random walks to capture long-range dependencies. We also employ multi-faceted loss functions to optimize for relevant recommendations while respecting the inherent sparsity of the data. Empirical evaluations demonstrate significant improvements over existing methods, with our model achieving a 43.1% increase in MRR. Furthermore, product teams who consumed these features perceive the feature as useful and rated it 4.5 out of 5.

cs.LG↗

arXiv2025

Synergistic Weak-Strong Collaboration by Aligning Preferences

Current Large Language Models (LLMs) excel in general reasoning yet struggle with specialized tasks requiring proprietary or domain-specific knowledge. Fine-tuning large models for every niche application is often infeasible due to black-box constraints and high computational overhead. To address this, we propose a collaborative framework that pairs a specialized weak model with a general strong model. The weak model, tailored to specific domains, produces initial drafts and background information, while the strong model leverages its advanced reasoning to refine these drafts, extending LLMs' capabilities to critical yet specialized tasks. To optimize this collaboration, we introduce a collaborative feedback to fine-tunes the weak model, which quantifies the influence of the weak model's contributions in the collaboration procedure and establishes preference pairs to guide preference tuning of the weak model. We validate our framework through experiments on three domains. We find that the collaboration significantly outperforms each model alone by leveraging complementary strengths. Moreover, aligning the weak model with the collaborative preference further enhances overall performance.

cs.AI↗

arXiv2025

UFO2: The Desktop AgentOS

Recent Computer-Using Agents (CUAs), powered by multimodal large language models (LLMs), offer a promising direction for automating complex desktop workflows through natural language. However, most existing CUAs remain conceptual prototypes, hindered by shallow OS integration, fragile screenshot-based interaction, and disruptive execution. We present UFO2, a multiagent AgentOS for Windows desktops that elevates CUAs into practical, system-level automation. UFO2 features a centralized HostAgent for task decomposition and coordination, alongside a collection of application-specialized AppAgent equipped with native APIs, domain-specific knowledge, and a unified GUI--API action layer. This architecture enables robust task execution while preserving modularity and extensibility. A hybrid control detection pipeline fuses Windows UI Automation (UIA) with vision-based parsing to support diverse interface styles. Runtime efficiency is further enhanced through speculative multi-action planning, reducing per-step LLM overhead. Finally, a Picture-in-Picture (PiP) interface enables automation within an isolated virtual desktop, allowing agents and users to operate concurrently without interference. We evaluate UFO2 across over 20 real-world Windows applications, demonstrating substantial improvements in robustness and execution accuracy over prior CUAs. Our results show that deep OS integration unlocks a scalable path toward reliable, user-aligned desktop automation.

cs.AI↗

arXiv2025

LangCoop: Collaborative Driving with Language

Multi-agent collaboration holds great promise for enhancing the safety, reliability, and mobility of autonomous driving systems by enabling information sharing among multiple connected agents. However, existing multi-agent communication approaches are hindered by limitations of existing communication media, including high bandwidth demands, agent heterogeneity, and information loss. To address these challenges, we introduce LangCoop, a new paradigm for collaborative autonomous driving that leverages natural language as a compact yet expressive medium for inter-agent communication. LangCoop features two key innovations: Mixture Model Modular Chain-of-thought (M$^3$CoT) for structured zero-shot vision-language reasoning and Natural Language Information Packaging (LangPack) for efficiently packaging information into concise, language-based messages. Through extensive experiments conducted in the CARLA simulations, we demonstrate that LangCoop achieves a remarkable 96\% reduction in communication bandwidth (< 2KB per message) compared to image-based communication, while maintaining competitive driving performance in the closed-loop evaluation. Our project page and code are at https://xiangbogaobarry.github.io/LangCoop/.

cs.RO↗

arXiv2025

An Empirical Study of Production Incidents in Generative AI Cloud Services

The ever-increasing demand for generative artificial intelligence (GenAI) has motivated cloud-based GenAI services such as Azure OpenAI Service and Amazon Bedrock. Like any large-scale cloud service, failures are inevitable in cloud-based GenAI services, resulting in user dissatisfaction and significant monetary losses. However, GenAI cloud services, featured by their massive parameter scales, hardware demands, and usage patterns, present unique challenges, including generated content quality issues and privacy concerns, compared to traditional cloud services. To understand the production reliability of GenAI cloud services, we analyzed production incidents from a leading GenAI cloud service provider spanning in the past four years. Our study (1) presents the general characteristics of GenAI cloud service incidents at different stages of the incident life cycle; (2) identifies the symptoms and impacts of these incidents on GenAI cloud service quality and availability; (3) uncovers why these incidents occurred and how they were resolved; (4) discusses open research challenges in terms of incident detection, triage, and mitigation, and sheds light on potential solutions.

cs.DC↗

arXiv2025

CoCMT: Communication-Efficient Cross-Modal Transformer for Collaborative Perception

Multi-agent collaborative perception enhances each agent perceptual capabilities by sharing sensing information to cooperatively perform robot perception tasks. This approach has proven effective in addressing challenges such as sensor deficiencies, occlusions, and long-range perception. However, existing representative collaborative perception systems transmit intermediate feature maps, such as bird-eye view (BEV) representations, which contain a significant amount of non-critical information, leading to high communication bandwidth requirements. To enhance communication efficiency while preserving perception capability, we introduce CoCMT, an object-query-based collaboration framework that optimizes communication bandwidth by selectively extracting and transmitting essential features. Within CoCMT, we introduce the Efficient Query Transformer (EQFormer) to effectively fuse multi-agent object queries and implement a synergistic deep supervision to enhance the positive reinforcement between stages, leading to improved overall performance. Experiments on OPV2V and V2V4Real datasets show CoCMT outperforms state-of-the-art methods while drastically reducing communication needs. On V2V4Real, our model (Top-50 object queries) requires only 0.416 Mb bandwidth, 83 times less than SOTA methods, while improving AP70 by 1.1 percent. This efficiency breakthrough enables practical collaborative perception deployment in bandwidth-constrained environments without sacrificing detection accuracy.

cs.LG↗

arXiv2025

SageServe: Optimizing LLM Serving on Cloud Data Centers with Forecast Aware Auto-Scaling

Global cloud service providers handle inference workloads for Large Language Models (LLMs) that span latency-sensitive (e.g., chatbots) and insensitive (e.g., report writing) tasks, resulting in diverse and often conflicting Service Level Agreement (SLA) requirements. Managing such mixed workloads is challenging due to the complexity of the inference serving stack, which encompasses multiple models, GPU hardware, and global data centers. Existing solutions often silo such fast and slow tasks onto separate GPU resource pools with different SLAs, but this leads to significant under-utilization of expensive accelerators due to load mismatch. In this article, we characterize the LLM serving workloads at Microsoft Office 365, one of the largest users of LLMs within Microsoft Azure cloud with over 10 million requests per day, and highlight key observations across workloads in different data center regions and across time. This is one of the first such public studies of Internet-scale LLM workloads. We use these insights to propose SageServe, a comprehensive LLM serving framework that dynamically adapts to workload demands using multi-timescale control knobs. It combines short-term request routing to data centers with long-term scaling of GPU VMs and model placement with higher lead times, and co-optimizes the routing and resource allocation problem using a traffic forecast model and an Integer Linear Programming (ILP) solution. We evaluate SageServe through real runs and realistic simulations on 10 million production requests across three regions and four open-source models. We achieve up to 25% savings in GPU-hours compared to the current baseline deployment and reduce GPU-hour wastage due to inefficient auto-scaling by 80%, resulting in a potential monthly cost savings of up to $2.5 million, while maintaining tail latency and meeting SLAs.

cs.DC↗

arXiv2025

AIOpsLab: A Holistic Framework to Evaluate AI Agents for Enabling Autonomous Clouds

AI for IT Operations (AIOps) aims to automate complex operational tasks, such as fault localization and root cause analysis, to reduce human workload and minimize customer impact. While traditional DevOps tools and AIOps algorithms often focus on addressing isolated operational tasks, recent advances in Large Language Models (LLMs) and AI agents are revolutionizing AIOps by enabling end-to-end and multitask automation. This paper envisions a future where AI agents autonomously manage operational tasks throughout the entire incident lifecycle, leading to self-healing cloud systems, a paradigm we term AgentOps. Realizing this vision requires a comprehensive framework to guide the design, development, and evaluation of these agents. To this end, we present AIOPSLAB, a framework that not only deploys microservice cloud environments, injects faults, generates workloads, and exports telemetry data but also orchestrates these components and provides interfaces for interacting with and evaluating agents. We discuss the key requirements for such a holistic framework and demonstrate how AIOPSLAB can facilitate the evaluation of next-generation AIOps agents. Through evaluations of state-of-the-art LLM agents within the benchmark created by AIOPSLAB, we provide insights into their capabilities and limitations in handling complex operational tasks in cloud environments.

cs.AI↗

arXiv2024

Ensuring Fair LLM Serving Amid Diverse Applications

In a multi-tenant large language model (LLM) serving platform hosting diverse applications, some users may submit an excessive number of requests, causing the service to become unavailable to other users and creating unfairness. Existing fairness approaches do not account for variations in token lengths across applications and multiple LLM calls, making them unsuitable for such platforms. To address the fairness challenge, this paper analyzes millions of requests from thousands of users on MS CoPilot, a real-world multi-tenant LLM platform hosted by Microsoft. Our analysis confirms the inadequacy of existing methods and guides the development of FairServe, a system that ensures fair LLM access across diverse applications. FairServe proposes application-characteristic aware request throttling coupled with a weighted service counter based scheduling technique to curb abusive behavior and ensure fairness. Our experimental results on real-world traces demonstrate FairServe's superior performance compared to the state-of-the-art method in ensuring fairness. We are actively working on deploying our system in production, expecting to benefit millions of customers world-wide.

cs.LG↗

arXiv2024

Intelligent Router for LLM Workloads: Improving Performance Through Workload-Aware Load Balancing

Large Language Model (LLM) workloads have distinct prefill and decode phases with different compute and memory requirements which should ideally be accounted for when scheduling input queries across different LLM instances in a cluster. However existing scheduling algorithms treat LLM workloads as monolithic jobs without considering the distinct characteristics of the two phases in each workload. This leads to sub-optimal scheduling and increased response latency. In this work, we start by characterizing factors affecting the response latency during LLM inference serving. We establish that better load balancing of inference requests across the available LLM instances can improve the end-to-end latency to a larger extent than merely focusing on optimizing the instance-level scheduler. Motivated by our findings, we propose a heuristic-guided reinforcement learning-based intelligent router for data-driven and workload-aware scheduling. Our router schedules queries across LLM instances by leveraging a trainable response-length predictor, and a novel formulation for estimating the impact of mixing different workloads and achieves over 11% lower end-to-end latency than existing approaches on a mix of public datasets and 7.8% lower end-to-end latency on real workload data with diverse input and output trends from Cloud Provider X. Additionally, the proposed framework can also serve as a standard for benchmarking different LLM inference schedulers since it provides the best latency for a given model, hardware, and instance-level scheduler combination.

cs.DC↗

arXiv2024

Automated Root Causing of Cloud Incidents using In-Context Learning with GPT-4

Root Cause Analysis (RCA) plays a pivotal role in the incident diagnosis process for cloud services, requiring on-call engineers to identify the primary issues and implement corrective actions to prevent future recurrences. Improving the incident RCA process is vital for minimizing service downtime, customer impact and manual toil. Recent advances in artificial intelligence have introduced state-of-the-art Large Language Models (LLMs) like GPT-4, which have proven effective in tackling various AIOps problems, ranging from code authoring to incident management. Nonetheless, the GPT-4 model's immense size presents challenges when trying to fine-tune it on user data because of the significant GPU resource demand and the necessity for continuous model fine-tuning with the emergence of new data. To address the high cost of fine-tuning LLM, we propose an in-context learning approach for automated root causing, which eliminates the need for fine-tuning. We conduct extensive study over 100,000 production incidents, comparing several large language models using multiple metrics. The results reveal that our in-context learning approach outperforms the previous fine-tuned large language models such as GPT-3 by an average of 24.8\% across all metrics, with an impressive 49.7\% improvement over the zero-shot model. Moreover, human evaluation involving actual incident owners demonstrates its superiority over the fine-tuned model, achieving a 43.5\% improvement in correctness and an 8.7\% enhancement in readability. The impressive results demonstrate the viability of utilizing a vanilla GPT model for the RCA task, thereby avoiding the high computational and maintenance costs associated with a fine-tuned model.

cs.CL↗

arXiv2023

PIMMiner: A High-performance PIM Architecture-aware Graph Mining Framework

Graph mining applications, such as subgraph pattern matching and mining, are widely used in real-world domains such as bioinformatics, social network analysis, and computer vision. Such applications are considered a new class of data-intensive applications that generate massive irregular computation workloads and memory accesses, which degrade the performance significantly. Leveraging emerging hardware, such as process-in-memory (PIM) technology, could potentially accelerate such applications. In this paper, we propose PIMMiner, a high-performance PIM architecture graph mining framework. We first identify that current PIM architecture cannot be fully utilized by graph mining applications. Next, we propose a set of optimizations and interfaces that enhance the locality, and internal bandwidth utilization and reduce remote bank accesses and load imbalance through cohesive algorithm and architecture co-designs. We compare PIMMiner with several state-of-the-art graph mining frameworks and show that PIMMiner is able to outperform all of them significantly.

cs.AR↗

arXiv2022

EHAP-ORAM: Efficient Hardware-Assisted Persistent ORAM System for Non-volatile Memory

Oblivious RAM (ORAM) is a provable secure primitive to prevent access pattern leakage on the memory bus. It serves as the intermediate layer between the trusted on-chip components and the untrusted external memory systems to modulate the original memory access patterns into indistinguishable memory sequences. By randomly remapping the data blocks and accessing redundant blocks, ORAM prevents access pattern leakage through obfuscation. While there is much prior work focusing on improving ORAM's performance on the conventional DRAM-based memory system, when the memory technology shifts to use non-volatile memory (NVM), new challenges come up as to how to efficiently support crash consistency for ORAM. In this work, we propose EHAP-ORAM, which studies how to persist ORAM construction with an NVM-based memory system. We first analyze the design requirements for a persistent ORAM system and discuss the need to preserve crash consistency and atomicity for both data and ORAM metadata. Next, we discuss some of the challenges in the design of a persistent ORAM system and propose some solutions to those challenges. Then, we propose the modified on-chip ORAM controller architecture. Based on the improved hardware architecture of the ORAM controller on-chip, we propose different persistency protocols to ensure the crash consistency of the ORAM system and satisfy that the metadata in PosMap is safe when it is persisted to NVM in trusted/untrusted off-chip. The proposed architecture and persistency protocol steps minimize the overhead and leakage during the write-back process. Finally, we compared our persistent ORAM with the system without crash consistency support, show that in non-recursive and recursive cases, EHAP-ORAM only incurs 3.36% and 3.65% performance overhead. The results show that the EHAP-ORAM can support efficient crash consistency with minimal performance and hardware overhead.

cs.AR↗

arXiv2021

Efficient Mining of Frequent Subgraphs with Two-Vertex Exploration

Frequent Subgraph Mining (FSM) is the key task in many graph mining and machine learning applications. Numerous systems have been proposed for FSM in the past decade. Although these systems show good performance for small patterns (with no more than four vertices), we found that they have difficulty in mining larger patterns. In this work, we propose a novel two-vertex exploration strategy to accelerate the mining process. Compared with the single-vertex exploration adopted by previous systems, our two-vertex exploration avoids the large memory consumption issue and significantly reduces the memory access overhead. We further enhance the performance through an index-based quick pattern technique that reduces the overhead of isomorphism checks, and a subgraph sampling technique that mitigates the issue of subgraph explosion. The experimental results show that our system achieves significant speedups against the state-of-the-art graph pattern mining systems and supports larger pattern mining tasks that none of the existing systems can handle.

cs.DB↗