Publications (116)
DoVer: Intervention-Driven Auto Debugging for LLM Multi-Agent Systems
Ming Ma, Jue Zhang, Fangkai Yang +4
Large language model (LLM)-based multi-agent systems are challenging to debug because failures often arise from long, branching interaction traces. The prevailing practice is to le…
AllHands: Ask Me Anything on Large-scale Verbatim Feedback via Large Language Models
Chaoyun Zhang, Zicheng Ma, Yuhao Wu +12
Verbatim feedback constitutes a valuable repository of user experiences, opinions, and requirements essential for software development. Effectively and efficiently extracting valua…
WarriorCoder: Learning from Expert Battles to Augment Code Large Language Models
Huawen Feng, Pu Zhao, Qingfeng Sun +8
Despite recent progress achieved by code large language models (LLMs), their remarkable abilities are largely dependent on fine-tuning on the high-quality data, posing challenges f…
Text2Grad: Reinforcement Learning from Natural Language Feedback
Hanyang Wang, Lu Wang, Chaoyun Zhang +5
Traditional RLHF optimizes language models with coarse, scalar rewards that mask the fine-grained reasons behind success or failure, leading to slow and opaque learning. Recent wor…
From Reasoning to Answer: Empirical, Attention-Based and Mechanistic Insights into Distilled DeepSeek R1 Models
Jue Zhang, Qingwei Lin, Saravan Rajmohan +1
Large Reasoning Models (LRMs) generate explicit reasoning traces alongside final answers, yet the extent to which these traces influence answer generation remains unclear. In this…
Nissist: An Incident Mitigation Copilot based on Troubleshooting Guides
Kaikai An, Fangkai Yang, Junting Lu +11
Effective incident management is pivotal for the smooth operation of enterprises-level cloud services. In order to expedite incident mitigation, service teams compile troubleshooti…
Self-Evolved Reward Learning for LLMs
Chenghua Huang, Zhizhen Fan, Lu Wang +7
Reinforcement Learning from Human Feedback (RLHF) is a crucial technique for aligning language models with human preferences, playing a pivotal role in the success of conversationa…
Large Language Model-Brained GUI Agents: A Survey
Chaoyun Zhang, Shilin He, Jiaxu Qian +10
GUIs have long been central to human-computer interaction, providing an intuitive and visually-driven way to access and interact with digital systems. The advent of LLMs, particula…
An Advanced Reinforcement Learning Framework for Online Scheduling of Deferrable Workloads in Cloud Computing
Hang Dong, Liwen Zhu, Zhao Shan +10
Efficient resource utilization and perfect user experience usually conflict with each other in cloud computing platforms. Great efforts have been invested in increasing resource ut…
Enhanced Fairness Testing via Generating Effective Initial Individual Discriminatory Instances
Minghua Ma, Zhao Tian, Max Hort +4
Fairness testing aims at mitigating unintended discrimination in the decision-making process of data-driven AI systems. Individual discrimination may occur when an AI model makes d…
Conservative State Value Estimation for Offline Reinforcement Learning
Liting Chen, Jie Yan, Zhengdao Shao +5
Offline reinforcement learning faces a significant challenge of value over-estimation due to the distributional drift between the dataset and the current learned policy, leading to…
Augmented Large Language Models with Parametric Knowledge Guiding
Ziyang Luo, Can Xu, Pu Zhao +5
Large Language Models (LLMs) have significantly advanced natural language processing (NLP) with their impressive language understanding and generation capabilities. However, their…
Why does Prediction Accuracy Decrease over Time? Uncertain Positive Learning for Cloud Failure Prediction
Haozhe Li, Minghua Ma, Yudong Liu +8
With the rapid growth of cloud computing, a variety of software services have been deployed in the cloud. To ensure the reliability of cloud services, prior studies focus on failur…
Thread: A Logic-Based Data Organization Paradigm for How-To Question Answering with Retrieval Augmented Generation
Kaikai An, Fangkai Yang, Liqun Li +10
Recent advances in retrieval-augmented generation (RAG) have substantially improved question-answering systems, particularly for factoid '5Ws' questions. However, significant chall…
Xpert: Empowering Incident Management with Query Recommendations via Large Language Models
Yuxuan Jiang, Chaoyun Zhang, Shilin He +8
Large-scale cloud systems play a pivotal role in modern IT infrastructure. However, incidents occurring within these systems can lead to service disruptions and adversely affect us…
Large Action Models: From Inception to Implementation
Lu Wang, Fangkai Yang, Chaoyun Zhang +15
As AI continues to advance, there is a growing demand for systems that go beyond language-based assistance and move toward intelligent agents capable of performing real-world actio…
A Tale of Two Graphs: Separating Knowledge Exploration from Outline Structure for Open-Ended Deep Research
Zhuofan Shi, Ming Ma, Zekun Yao +7
Open-Ended Deep Research (OEDR) pushes LLM agents beyond short-form QA toward long-horizon workflows that iteratively search, connect, and synthesize evidence into structured repor…
Can Large Language Models Generate Observability-Aware Code?
Yongliang Tao, Hongyu Zhang, Pengfei Gao +8
Recent advances in coding agents have enabled the generation of increasingly complex software systems. While existing evaluations primarily focus on functional correctness, product…
Safe and Balanced: A Framework for Constrained Multi-Objective Reinforcement Learning
Shangding Gu, Bilgehan Sel, Yuhao Ding +4
In numerous reinforcement learning (RL) problems involving safety-critical systems, a key challenge lies in balancing multiple objectives while simultaneously meeting all stringent…
Diffusion-based Time Series Data Imputation for Microsoft 365
Fangkai Yang, Wenjie Yin, Lu Wang +10
Reliability is extremely important for large-scale cloud systems like Microsoft 365. Cloud failures such as disk failure, node failure, etc. threaten service reliability, resulting…
Did We Miss Something Important? Studying and Exploring Variable-Aware Log Abstraction
Zhenhao Li, Chuan Luo, Tse-Hsun Chen +4
Due to the sheer size of software logs, developers rely on automated techniques for log analysis. One of the first and most important steps of automated log analysis is log abstrac…
RepoGenesis: Benchmarking End-to-End Microservice Generation from Readme to Repository
Zhiyuan Peng, Xin Yin, Pu Zhao +7
Large language models and agents have achieved remarkable progress in code generation. However, existing benchmarks focus on isolated function/class-level generation (e.g., ClassEv…
UFO3: Weaving the Digital Agent Galaxy
Chaoyun Zhang, Liqun Li, He Huang +8
Large language model (LLM)-powered agents are transforming digital devices from passive tools into proactive intelligent collaborators. However, most existing frameworks remain con…
Revisiting VAE for Unsupervised Time Series Anomaly Detection: A Frequency Perspective
Zexin Wang, Changhua Pei, Minghua Ma +9
Time series Anomaly Detection (AD) plays a crucial role for web systems. Various web systems rely on time series data to monitor and identify anomalies in real time, as well as to…
DI-BENCH: Benchmarking Large Language Models on Dependency Inference with Testable Repositories at Scale
Linghao Zhang, Junhao Wang, Shilin He +13
Large Language Models have advanced automated software development, however, it remains a challenge to correctly infer dependencies, namely, identifying the internal components and…
LoopsBench: From Harness Engineering to Loop Engineering in Benchmarking Coding Agent
Han Li, Zhemin Fang, Rili Feng +8
Coding agent infrastructure is shifting from harness engineering toward loop engineering as coding agents are deployed for sustained long-horizon software development. Existing ben…
WizardCoder: Empowering Code Large Language Models with Evol-Instruct
Ziyang Luo, Can Xu, Pu Zhao +7
Code Large Language Models (Code LLMs), such as StarCoder, have demonstrated exceptional performance in code-related tasks. However, most existing models are solely pre-trained on…
Fast Outage Analysis of Large-scale Production Clouds with Service Correlation Mining
Yaohui Wang, Guozheng Li, Zijian Wang +13
Cloud-based services are surging into popularity in recent years. However, outages, i.e., severe incidents that always impact multiple services, can dramatically affect user experi…
DUET: Joint Exploration of User Item Profiles in Recommendation System
Yue Chen, Yifei Sun, Lu Wang +17
Traditional recommendation systems represent users and items as dense vectors and learn to align them in a shared latent space for relevance estimation. Recent LLM-based recommende…
Everything of Thoughts: Defying the Law of Penrose Triangle for Thought Generation
Ruomeng Ding, Chaoyun Zhang, Lu Wang +7
Recent advancements in Large Language Models (LLMs) have revolutionized decision-making by breaking down complex problems into more manageable language sequences referred to as "th…
ORACLE-SWE: Quantifying the Contribution of Oracle Information Signals on SWE Agents
Kenan Li, Qirui Jin, Liao Zhu +13
Recent advances in language model (LM) agents have significantly improved automated software engineering (SWE). Prior work has proposed various agentic workflows and training strat…
Privacy in Action: Towards Realistic Privacy Mitigation and Evaluation for LLM-Powered Agents
Shouju Wang, Fenglin Yu, Xirui Liu +5
The increasing autonomy of LLM agents in handling sensitive communications, accelerated by Model Context Protocol (MCP) and Agent-to-Agent (A2A) frameworks, creates urgent privacy…
RepoLaunch: Automating Build and Management of Code Repositories across Languages and Platforms
Kenan Li, Rongzhi Li, Linghao Zhang +17
Language model (LM) agents have driven substantial progress in automated software engineering (SWE), yet building and testing software repositories at scale remains a largely manua…
From Task to Tutorial: An Automated GUI Framework for Excel Tutorial Document and Video Creation
Yuhang Xie, Jian Mu, Xiaojun Ma +9
Excel is one of the most widely used productivity tools across domains, offering rich functionality but also overwhelming users with its complexity. This creates a persistent deman…
Distill Not Only Data but Also Rewards: Can Smaller Language Models Surpass Larger Ones?
Yudi Zhang, Lu Wang, Meng Fang +8
Distilling large language models (LLMs) typically involves transferring the teacher model's responses through supervised fine-tuning (SFT). However, this approach neglects the pote…
Counter-Empirical Attacking based on Adversarial Reinforcement Learning for Time-Relevant Scoring System
Xiangguo Sun, Hong Cheng, Hang Dong +3
Scoring systems are commonly seen for platforms in the era of big data. From credit scoring systems in financial services to membership scores in E-commerce shopping platforms, pla…
GUI-360: A Comprehensive Dataset and Benchmark for Computer-Using Agents
Jian Mu, Chaoyun Zhang, Chiming Ni +14
We introduce GUI-360, a large-scale, comprehensive dataset and benchmark suite designed to advance computer-using agents (CUAs). CUAs present unique challenges and is const…
LLM Reasoning as Trajectories: Step-Specific Representation Geometry and Correctness Signals
Lihao Sun, Hang Dong, Bo Qiao +3
This work characterizes large language models' chain-of-thought generation as a structured trajectory through representation space. We show that mathematical reasoning traverses fu…
RCInvestigator: Towards Better Investigation of Anomaly Root Causes in Cloud Computing Systems
Shuhan Liu, Yunfan Zhou, Lu Ying +9
Finding the root causes of anomalies in cloud computing systems quickly is crucial to ensure availability and efficiency since accurate root causes can guide engineers to take appr…
Arena Learning: Build Data Flywheel for LLMs Post-training via Simulated Chatbot Arena
Haipeng Luo, Qingfeng Sun, Can Xu +6
Assessing the effectiveness of large language models (LLMs) presents substantial challenges. The method of conducting human-annotated battles in an online Chatbot Arena is a highly…
A Survey of Time Series Anomaly Detection Methods in the AIOps Domain
Zhenyu Zhong, Qiliang Fan, Jiacheng Zhang +6
Internet-based services have seen remarkable success, generating vast amounts of monitored key performance indicators (KPIs) as univariate or multivariate time series. Monitoring a…
ExeCoder: Empowering Large Language Models with Executability Representation for Code Translation
Minghua He, Yue Chen, Fangkai Yang +6
Code translation is a crucial activity in the software development and maintenance process, and researchers have recently begun to focus on using pre-trained large language models…
Zoomer: Adaptive Image Focus Optimization for Black-box MLLM
Jiaxu Qian, Chendong Wang, Yifan Yang +16
Multimodal large language models (MLLMs) such as GPT-4o, Gemini Pro, and Claude 3.5 have enabled unified reasoning over text and visual inputs, yet they often hallucinate in real w…
WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct
Haipeng Luo, Qingfeng Sun, Can Xu +8
Large language models (LLMs), such as GPT-4, have shown remarkable performance in natural language processing (NLP) tasks, including challenging mathematical reasoning. However, mo…
Automatic Root Cause Analysis via Large Language Models for Cloud Incidents
Yinfang Chen, Huaibing Xie, Minghua Ma +15
Ensuring the reliability and availability of cloud services necessitates efficient root cause analysis (RCA) for cloud incidents. Traditional RCA methods, which rely on manual inve…
Enabling Autonomic Microservice Management through Self-Learning Agents
Fenglin Yu, Fangkai Yang, Xiaoting Qin +8
The increasing complexity of modern software systems necessitates robust autonomic self-management capabilities. While Large Language Models (LLMs) demonstrate potential in this do…
AutoRAG-HP: Automatic Online Hyper-Parameter Tuning for Retrieval-Augmented Generation
Jia Fu, Xiaoting Qin, Fangkai Yang +7
Recent advancements in Large Language Models have transformed ML/AI development, necessitating a reevaluation of AutoML principles for the Retrieval-Augmented Generation (RAG) syst…
GUI-Actor: Coordinate-Free Visual Grounding for GUI Agents
Qianhui Wu, Kanzhi Cheng, Rui Yang +15
One of the principal challenges in building VLM-powered GUI agents is visual grounding, i.e., localizing the appropriate screen region for action execution based on both the visual…
Learning Cooperative Oversubscription for Cloud by Chance-Constrained Multi-Agent Reinforcement Learning
Junjie Sheng, Lu Wang, Fangkai Yang +9
Oversubscription is a common practice for improving cloud resource utilization. It allows the cloud service provider to sell more resources than the physical limit, assuming not al…
Distributed Evolution Strategies for Black-box Stochastic Optimization
Xiaoyu He, Zibin Zheng, Chuan Chen +3
This work concerns the evolutionary approaches to distributed stochastic black-box optimization, in which each worker can individually solve an approximation of the problem with na…
Contrastive Attribution in the Wild: An Interpretability Analysis of LLM Failures on Realistic Benchmarks
Rongyuan Tan, Jue Zhang, Zhuozhao Li +3
Interpretability tools are increasingly used to analyze failures of Large Language Models (LLMs), yet prior work largely focuses on short prompts or toy settings, leaving their beh…
UniParser: A Unified Log Parser for Heterogeneous Log Data
Yudong Liu, Xu Zhang, Shilin He +9
Logs provide first-hand information for engineers to diagnose failures in large-scale online service systems. Log parsing, which transforms semi-structured raw log messages into st…
Contrastive Learning with Negative Sampling Correction
Lu Wang, Chao Du, Pu Zhao +8
As one of the most effective self-supervised representation learning methods, contrastive learning (CL) relies on multiple negative pairs to contrast against each positive pair. In…
ToolAtlas: Learning Once, Reusing Everywhere with Tool-Side Memory
Yue Fang, Zhibang Yang, Fangkai Yang +5
ToolAtlas introduces a graph‑based, provider‑side memory that records tool capabilities, failure limits, and how tools can be combined, allowing LLM agents to query this memory and…
The Ensemble Approach of Column Generation for Solving Cutting Stock Problems
Mingjie Hu, Jie Yan, Liting Chen +1
This paper investigates the column generation (CG) for solving cutting stock problems (CSP). Traditional CG method, which repeatedly solves a restricted master problem (RMP), often…
Skeleton-Guided-Translation: A Benchmarking Framework for Code Repository Translation with Fine-Grained Quality Evaluation
Xing Zhang, Jiaheng Wen, Fangkai Yang +11
The advancement of large language models has intensified the need to modernize enterprise applications and migrate legacy systems to secure, versatile languages. However, existing…
Computer-Using World Model
Yiming Guan, Rui Yu, John Zhang +15
Agents operating in complex software environments benefit from reasoning about the consequences of their actions, as even a single incorrect user interface (UI) operation can derai…
Call Me When Necessary: LLMs can Efficiently and Faithfully Reason over Structured Environments
Sitao Cheng, Ziyuan Zhuang, Yong Xu +9
Large Language Models (LLMs) have shown potential in reasoning over structured environments, e.g., knowledge graph and table. Such tasks typically require multi-hop reasoning, i.e.…
EfficientRAG: Efficient Retriever for Multi-Hop Question Answering
Ziyuan Zhuang, Zhiyang Zhang, Sitao Cheng +7
Retrieval-augmented generation (RAG) methods encounter difficulties when addressing complex questions like multi-hop queries. While iterative retrieval methods improve performance…
Incident-aware Duplicate Ticket Aggregation for Cloud Systems
Jinyang Liu, Shilin He, Zhuangbin Chen +10
In cloud systems, incidents are potential threats to customer satisfaction and business revenue. When customers are affected by incidents, they often request customer support servi…
Solving the Batch Stochastic Bin Packing Problem in Cloud: A Chance-constrained Optimization Approach
Jie Yan, Yunlei Lu, Liting Chen +6
This paper investigates a critical resource allocation problem in the first party cloud: scheduling containers to machines. There are tens of services and each service runs a set o…
AdNanny: One Reasoning LLM for All Offline Ads Recommendation Tasks
Nan Hu, Han Li, Jimeng Sun +16
Large Language Models (LLMs) have shown strong capabilities in Natural Language Understanding and Generation, but deploying them directly in online advertising systems is often imp…
Empower Large Language Model to Perform Better on Industrial Domain-Specific Question Answering
Fangkai Yang, Pu Zhao, Zezhong Wang +6
Large Language Model (LLM) has gained popularity and achieved remarkable results in open-domain tasks, but its performance in real industrial domain-specific scenarios is average d…
Towards a Systems Foundation for Agentic Cloud Management
Minghao Li, Ziqian Liu, Ziyu Mao +5
The paper proposes CloudWeaver, a systems layer that lets autonomous agents safely manage cloud resources by providing scoped views and coordinating concurrent operations, ensuring…
Learning to Refine: Self-Refinement of Parallel Reasoning in LLMs
Qibin Wang, Pu Zhao, Shaohan Huang +6
Test-time scaling (TTS) has gained widespread attention for enhancing LLM reasoning. Existing approaches such as Best-of-N and majority voting are limited as their performance depe…
Risk-aware Adaptive Virtual CPU Oversubscription in Microsoft Cloud via Prototypical Human-in-the-loop Imitation Learning
Lu Wang, Mayukh Das, Fangkai Yang +11
Oversubscription is a prevalent practice in cloud services where the system offers more virtual resources, such as virtual cores in virtual machines, to users or applications than…
SWE-bench Goes Live!
Linghao Zhang, Shilin He, Chaoyun Zhang +12
The issue-resolving task, where a model generates patches to fix real-world bugs, has emerged as a critical benchmark for evaluating the capabilities of large language models (LLMs…
Assess and Summarize: Improve Outage Understanding with Large Language Models
Pengxiang Jin, Shenglin Zhang, Minghua Ma +13
Cloud systems have become increasingly popular in recent years due to their flexibility and scalability. Each time cloud computing applications and services hosted on the cloud are…
Label Mapping Neural Networks with Response Consolidation for Class Incremental Learning
Xu Zhang, Yang Yao, Baile Xu +4
Class incremental learning refers to a special multi-class classification task, in which the number of classes is not fixed but is increasing with the continual arrival of new data…
RePrompt: Reasoning-Augmented Reprompting for Text-to-Image Generation via Reinforcement Learning
Mingrui Wu, Lu Wang, Pu Zhao +14
Despite recent progress in text-to-image (T2I) generation, existing models often struggle to faithfully capture user intentions from short and under-specified prompts. While prior…
TaskWeaver: A Code-First Agent Framework
Bo Qiao, Liqun Li, Xu Zhang +16
Large Language Models (LLMs) have shown impressive abilities in natural language understanding and generation, leading to their widespread use in applications such as chatbots and…
Deoxys: A Causal Inference Engine for Unhealthy Node Mitigation in Large-scale Cloud Infrastructure
Chaoyun Zhang, Randolph Yao, Si Qin +8
The presence of unhealthy nodes in cloud infrastructure signals the potential failure of machines, which can significantly impact the availability and reliability of cloud services…
Beyond State Consistency: Behavior Consistency in Text-Based World Models
Youling Huang, Guanqiao Chen, Junchi Yao +8
World models have been emerging as critical components for assessing the consequences of actions generated by interactive agents in online planning and offline evaluation. In text-…
AdaptFlow: Adaptive Workflow Optimization via Meta-Learning
Runchuan Zhu, Bowen Jiang, Lingrui Mei +8
Recent advances in large language models (LLMs) have sparked growing interest in agentic workflows, which are structured sequences of LLM invocations intended to solve complex task…
Balance Reward and Safety Optimization for Safe Reinforcement Learning: A Perspective of Gradient Manipulation
Shangding Gu, Bilgehan Sel, Yuhao Ding +4
Ensuring the safety of Reinforcement Learning (RL) is crucial for its deployment in real-world applications. Nevertheless, managing the trade-off between reward and safety during e…
CI-Work: Benchmarking Contextual Integrity in Enterprise LLM Agents
Wenjie Fu, Xiaoting Qin, Jue Zhang +5
Enterprise LLM agents can dramatically improve workplace productivity, but their core capability, retrieving and using internal context to act on a user's behalf, also creates new…
Change2Task: From Repository Changes to Executable Coding Agent Tasks and Environments
Haomin Qi, Xingliang Wang, Xuanqi Gao +9
The paper introduces Change2Task, a system that turns merged pull requests from software repositories into verified, executable coding‑agent tasks by reconstructing the code state…
Verco: Learning Coordinated Verbal Communication for Multi-agent Reinforcement Learning
Dapeng Li, Hang Dong, Lu Wang +8
In recent years, multi-agent reinforcement learning algorithms have made significant advancements in diverse gaming environments, leading to increased interest in the broader appli…
AgentGen: Enhancing Planning Abilities for Large Language Model based Agent via Environment and Task Generation
Mengkang Hu, Pu Zhao, Can Xu +5
Large Language Model-based agents have garnered significant attention and are becoming increasingly popular. Furthermore, planning ability is a crucial component of an LLM-based ag…
LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression
Zhuoshi Pan, Qianhui Wu, Huiqiang Jiang +10
This paper focuses on task-agnostic prompt compression for better generalizability and efficiency. Considering the redundancy in natural language, existing approaches compress prom…
G-KV: Decoding-Time KV Cache Eviction with Global Attention
Mengqi Liao, Lu Wang, Chaoyun Zhang +7
Recent reasoning large language models (LLMs) excel in complex tasks but encounter significant computational and memory challenges due to long sequence lengths. KV cache compressio…
A Surrogate Objective Framework for Prediction+Optimization with Soft Constraints
Kai Yan, Jie Yan, Chuan Luo +3
Prediction+optimization is a common real-world paradigm where we have to predict problem parameters before solving the optimization problem. However, the criteria by which the pred…
AXIS: Efficient Human-Agent-Computer Interaction with API-First LLM-Based Agents
Junting Lu, Zhiyang Zhang, Fangkai Yang +7
Multimodal large language models (MLLMs) have enabled LLM-based agents to directly interact with application user interfaces (UIs), enhancing agents' performance in complex tasks.…
Navigating the Unknown: A Chat-Based Collaborative Interface for Personalized Exploratory Tasks
Yingzhe Peng, Xiaoting Qin, Zhiyang Zhang +6
The rise of large language models (LLMs) has revolutionized user interactions with knowledge-based systems, enabling chatbots to synthesize vast amounts of information and assist w…
MMDialog: A Large-scale Multi-turn Dialogue Dataset Towards Multi-modal Open-domain Conversation
Jiazhan Feng, Qingfeng Sun, Can Xu +5
Responding with multi-modal content has been recognized as an essential capability for an intelligent conversational agent. In this paper, we introduce the MMDialog dataset to bett…
AI Delegates with a Dual Focus: Ensuring Privacy and Strategic Self-Disclosure
Zhiyang Zhang, Xi Chen, Fangkai Yang +7
Large language model (LLM)-based AI delegates are increasingly utilized to act on behalf of users, assisting them with a wide range of tasks through conversational interfaces. Desp…
LettinGo: Explore User Profile Generation for Recommendation System
Lu Wang, Di Zhang, Fangkai Yang +9
User profiling is pivotal for recommendation systems, as it transforms raw user interaction data into concise and structured representations that drive personalized recommendations…
WizardLM: Empowering large pre-trained language models to follow complex instructions
Can Xu, Qingfeng Sun, Kai Zheng +6
Training large language models (LLMs) with open-domain instruction following data brings colossal success. However, manually creating such instruction data is very time-consuming a…
Token-level Proximal Policy Optimization for Query Generation
Yichen Ouyang, Lu Wang, Fangkai Yang +13
Query generation is a critical task for web search engines (e.g. Google, Bing) and recommendation systems. Recently, state-of-the-art query generation methods leverage Large Langua…
WebXSkill: Skill Learning for Autonomous Web Agents
Zhaoyang Wang, Qianhui Wu, Xuchao Zhang +12
Autonomous web agents powered by large language models (LLMs) have shown promise in completing complex browser tasks, yet they still struggle with long-horizon workflows. A key bot…
ImDiffusion: Imputed Diffusion Models for Multivariate Time Series Anomaly Detection
Yuhang Chen, Chaoyun Zhang, Minghua Ma +7
Anomaly detection in multivariate time series data is of paramount importance for ensuring the efficient operation of large-scale systems across diverse domains. However, accuratel…
VEM: Environment-Free Exploration for Training GUI Agent with Value Environment Model
Jiani Zheng, Lu Wang, Fangkai Yang +7
Training Vision-Language Models (VLMs) for Graphical User Interfaces (GUI) agents via Reinforcement Learning (RL) faces critical challenges: environment-based RL requires costly in…
UFO2: The Desktop AgentOS
Chaoyun Zhang, He Huang, Chiming Ni +18
Recent Computer-Using Agents (CUAs), powered by multimodal large language models (LLMs), offer a promising direction for automating complex desktop workflows through natural langua…
Sharingan: Extract User Action Sequence from Desktop Recordings
Yanting Chen, Yi Ren, Xiaoting Qin +7
Video recordings of user activities, particularly desktop recordings, offer a rich source of data for understanding user behaviors and automating processes. However, despite advanc…
RuAG: Learned-rule-augmented Generation for Large Language Models
Yudi Zhang, Pei Xiao, Lu Wang +11
In-context learning (ICL) and Retrieval-Augmented Generation (RAG) have gained attention for their ability to enhance LLMs' reasoning by incorporating external knowledge but suffer…
Robust Positive-Unlabeled Learning via Noise Negative Sample Self-correction
Zhangchi Zhu, Lu Wang, Pu Zhao +7
Learning from positive and unlabeled data is known as positive-unlabeled (PU) learning in literature and has attracted much attention in recent years. One common approach in PU lea…
Can Language Models Go Beyond Coding? Assessing the Capability of Language Models to Build Real-World Systems
Chenyu Zhao, Shenglin Zhang, Zeshun Huang +8
Large language models (LLMs) have shown growing potential in software engineering, yet few benchmarks evaluate their ability to repair software during migration across instruction…
Self-Guard: Empower the LLM to Safeguard Itself
Zezhong Wang, Fangkai Yang, Lu Wang +5
The jailbreak attack can bypass the safety measures of a Large Language Model (LLM), generating harmful content. This misuse of LLM has led to negative societal consequences. Curre…
StepFly: Agentic Troubleshooting Guide Automation for Incident Diagnosis
Jiayi Mao, Liqun Li, Yanjie Gao +9
Effective incident management in large-scale IT systems relies on troubleshooting guides (TSGs), but their manual execution is slow and error-prone. While recent advances in LLMs o…
Zipage: Maintain High Request Concurrency for LLM Reasoning through Compressed PagedAttention
Mengqi Liao, Lu Wang, Chaoyun Zhang +6
With reasoning becoming the generative paradigm for large language models (LLMs), the memory bottleneck caused by KV cache during the decoding phase has become a critical factor li…