姓名: 辜文蔚

职称: 讲师

电子邮箱: wwgu@nankai.edu.cn

学历: 博士研究生

所学专业: 计算机科学与工程

导师: 硕士生导师

研究方向: 多智能体驱动的智能运维、AI基础设施可靠性、多智能体系统可靠性、大模型训练可靠性

个人主页: https://nkcs.iops.ai/wenweigu/

个人简介

辜文蔚现为bw西汉姆联讲师。于2025年7月从香港中文大学计算机科学与工程系获得博士学位，师从软件可靠性工程领域先驱吕荣聪（Michael R. Lyu）教授（IEEE/ACM/AAAS Fellow，长江讲席教授）。在ICSE、FSE、ASE、TOSEM、TSE等CCF A/B国际顶尖会议和期刊发表高水平论文25篇。主持 CCF-蚂蚁科研基金、阿里巴巴校企合作项目等科研项目，并参与多项华为云、美团、字节跳动等企业合作项目。担任 ISSRE 2026、QRS 2026 程序委员会委员，2026 中国软件大会宣传委员会主席，第九届 CCF 国际智能运维挑战赛技术委员会主席；同时担任ICSE、ASE、FSE、TSE、TOSEM、TIFS、TON 等国际顶尖会议和期刊审稿人。

教育经历

2021.08-2025.07，香港中文大学，工学博士，计算机科学与工程专业（导师： 吕荣聪）

2017.09-2021.06，华中科技大学，工学学士，电子信息工程（卓越工程师计划班）专业

工作经历

2025.08-至今，bw西汉姆联，讲师

2025.02-2025.06，华为香港研究所，研究实习生

2022.01-2025.01，华为-港中文软件可靠性联合实验室，项目成员

2020.07-2020.08，香港中文大学深圳研究院，研究实习生

2019.07-2019.08，鹏城实验室，研究实习生

发表的部分论文:

1. ADAMAS: Adaptive Domain-Aware Performance Anomaly Detection in Cloud Service Systems

Wenwei Gu, Jiazhen Gu, Jinyang Liu, Zhuangbin Chen, Jianping Zhang, Jinxi Kuang, Cong Feng, Yongqiang Yang, and Michael R. Lyu

In Proceedings of the IEEE/ACM 47th International Conference on Software Engineering (ICSE), 2025 (CCF A)

2. Identifying Performance Issues in Cloud Service Systems Based on Relational-Temporal Features

Wenwei Gu, Jinyang Liu, Zhuangbin Chen, Jianping Zhang, Yuxin Su, Jiazhen Gu, Cong Feng, Zengyin Yang, Yongqiang Yang, and Michael R. Lyu

In ACM Transactions on Software Engineering and Methodology (TOSEM), 2024 (CCF A/SCI Q1)

3. KPIRoot: Efficient Monitoring Metric-based Root Cause Localization in Large-scale Cloud Systems

Wenwei Gu, Xinying Sun, Jinyang Liu, Yintong Huo, Zhuangbin Chen, Jianping Zhang, Jiazhen Gu, Yongqiang Yang, and Michael R. Lyu

In Proceedings of the 35th International Symposium on Software Reliability Engineering (ISSRE), 2024 (CCF B)

4. Cordial: Cross-row Failure Prediction Method Based on Bank-level Error Locality for HBMs

Wenwei Gu, Jiazhen Gu, Renyi Zhong, Wenyu Zhang, Ming Li, and Michael R. Lyu

In Proceedings of the 55th IEEE/IFIP International Conference on Dependable Systems and Networks (DSN), 2025 (CCF B)

5. KPIRoot+: An Efficient Integrated Framework for Anomaly Detection and Root Cause Analysis in Large-Scale Cloud Systems

Wenwei Gu, Renyi Zhong, Guangba Yu, Xinying Sun, Jinyang Liu, Yintong Huo, Zhuangbin Chen, Jianping Zhang, Jiazhen Gu, Yongqiang Yang, and Michael R. Lyu

In Empirical Software Engineering (EMSE), 2026 (CCF B/SCI Q2)

6. MERA: A Multi-Expert LLM Framework for Severity Assessment of User Tickets in Mobile OS Beta Testing

Yongqian Sun, Yimin Zuo, Qingliang Zhang, Bowen Hao, Wenwei Gu*, Jiaqi Luan, Sixu Zhou, Shenglin Zhang, and Dan Pei

In Proceedings of the 41st IEEE/ACM International Conference on Automated Software Engineering (ASE), 2026 (CCF A)

7. Curvature-Invariant Adversarial Attacks for 3D Point Clouds

Jianping Zhang, Wenwei Gu, Zhihan Jiang, Weibin Wu, and Michael R. Lyu

In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2024 (CCF A)

8. Revisiting, Benchmarking, and Exploring API Recommendation: How Far Are We?

Yun Peng, Shuqing Li, Wenwei Gu, Yichen Li, Wenxuan Wang, Cuiyun Gao, and Michael R. Lyu

In IEEE Transactions on Software Engineering (TSE), 2023 (CCF A/SCI Q1)

9. LogUpdater: Automated Detection and Repair of Specific Defects in Logging Statements

Renyi Zhong, Yichen Li, Jinxi Kuang, Wenwei Gu, Yintong Huo, and Michael R. Lyu

In ACM Transactions on Software Engineering and Methodology (TOSEM), 2025 (CCF A/SCI Q1)

10. LLMPrism: Black-box Performance Diagnosis for Production LLM Training Platforms

Zhihan Jiang, Rui Ren, Guangba Yu, Yulun Wu, Wenwei Gu, Yichen Li, Yujie Huang, Cong Feng, Zengyin Yang, Yongqiang Yang, and Michael R. Lyu

In Proceedings of the 55th IEEE/IFIP International Conference on Dependable Systems and Networks (DSN), 2025 (CCF B)

11. Integrating GraphSAGE and Mamba for Self-Supervised Spatio-Temporal Fault Detection in Microservice Systems

Shenglin Zhang, Yingke Li, Jianjin Tang, Chenyu Zhao, Wenwei Gu, Yongqian Sun, and Dan Pei

In Proceedings of the 36th International Symposium on Software Reliability Engineering (ISSRE), 2025 (CCF B)

12. Too Many Cooks: Assessing the Need for Multi-Source Data in Microservice Failure Diagnosis

Shenglin Zhang, Xiaoyu Feng, Runzhou Wang, Minghua Ma, Wenwei Gu, Yongqian Sun, Zedong Jia, Jinrui Sun, and Dan Pei

In Proceedings of the 36th International Symposium on Software Reliability Engineering (ISSRE), 2025 (CCF B，最佳论文奖提名)

13. AetherLog: Log-based Root Cause Analysis by Integrating Large Language Models with Knowledge Graphs

Tianyu Cui, Ruowei Fu, Changchang Liu, Yuhe Ji, Wenwei Gu, Shenglin Zhang, Yongqian Sun, and Dan Pei

In Proceedings of the 36th International Symposium on Software Reliability Engineering (ISSRE), 2025 (CCF B)

14. Adaptive Performance Regression Detection via Semi-Supervised Siamese Learning

Yongqian Sun, Mengyao Li, Xiao Xiong, Lei Tao, Yimin Zuo, Wenwei Gu, Shenglin Zhang, Junhua Kuang, Yu Luo, Huandong Zhuang, Bowen Deng, and Dan Pei

In Proceedings of the 40th IEEE/ACM International Conference on Automated Software Engineering (ASE), 2025 (CCF A)

15. Larger is Not Always Better: Exploring Small Open-Source Language Models in Logging Statement Generation

Renyi Zhong, Yichen Li, Guangba Yu, Wenwei Gu, Jinxi Kuang, Yintong Huo, and Michael R. Lyu

In ACM Transactions on Software Engineering and Methodology (TOSEM), 2026 (CCF A/SCI Q1)

16. PerfScout: An Adaptive Workload Generator in Software Performance Testing

Yongqian Sun, Qingliang Zhang, Xiao Xiong, Mengyao Li, Yimin Zuo, Shenglin Zhang, Xidao Wen, Wenwei Gu, Huandong Zhuang, Bowen Deng, Ruiyuan Wan, and Dan Pei

In Proceedings of the 48th IEEE/ACM International Conference on Software Engineering, Software Engineering in Practice Track (ICSE-SEIP), 2026 (CCF A)

17. When LLMs Listen to Experts: Accurate Failure Diagnosis in Operating Systems

Yongxin Zhao, Shenglin Zhang, Yuxin Sun, Wenwei Gu, Yongqian Sun, Luping Wang, Li Shi, Cheng Huang, Guodong Yang, Liping Zhang, and Dan Pei

In Proceedings of the 48th IEEE/ACM International Conference on Software Engineering, Software Engineering in Practice Track (ICSE-SEIP), 2026 (CCF A)

18. A Multi-Agent Framework for the End-to-End Automated Logging

Renyi Zhong, Yintong Huo, Wenwei Gu, Yichen Li, and Michael R. Lyu

In Proceedings of the 34th IEEE/ACM International Conference on Program Comprehension (ICPC), 2026 (CCF B)

19. Bridging the Delay: Lag-Aware Spatio-Temporal Causal Inference for Microservice Root Cause Analysis

Shenglin Zhang, Junhua Kuang, Yimeng Zhang, Sibo Xia, Jintao Feng, Jingyu Wang, Wenwei Gu, Yongqian Sun, Wei Li, Liping Zhang, and Dan Pei

In Proceedings of the ACM International Conference on the Foundations of Software Engineering (FSE), 2026 (CCF A，杰出论文奖)

20. Aloha: Localizing Batch Failures in Large-scale Cloud Systems via Contrast Analysis and Human-in-the-Loop Agent

Shenglin Zhang, Yujia Wu, Jinghuan Ren, Yongqian Sun, Wenwei Gu, Chaoyun Zhang, Liqun Li, Qingwei Lin, Dongmei Zhang, Saravanakumar Rajmohan, Chetan Bansal, and Minghua Ma

In Proceedings of the ACM International Conference on the Foundations of Software Engineering (FSE), 2026 (CCF A)

21. KRCA: An Efficient Root Cause Analysis System in Hyper-Scale Microservice Systems via Agentic AI

Jiamin Jiang, Jingfei Feng, Yu Luo, Qingliang Zhang, Yongqian Sun, Wenwei Gu, Shenglin Zhang, Tianyu Cui, Yao Wu, Jielong Huang, Nan Qi, and Dan Pei

In Proceedings of the 41st IEEE/ACM International Conference on Automated Software Engineering (ASE), 2026 (CCF A)

22. Debugging the Debuggers: Failure-Anchored Structured Recovery for Software Engineering Agents

Chenyu Zhao, Shenglin Zhang, Yihang Lin, Wenwei Gu, Zhimin Chen, Yongqian Sun, Dan Pei, Chetan Bansal, Saravan Rajmohan, and Minghua Ma

In Proceedings of the 41st IEEE/ACM International Conference on Automated Software Engineering (ASE), 2026 (CCF A)

23. LLM-Assisted Joint Ticket and Log Analysis for Incident Triage in Intelligent and Connected Vehicles

Ruowei Fu, Shenglin Zhang, Wenwei Gu, Weiguo Li, Yongqian Sun, and Dan Pei

In Proceedings of the 41st IEEE/ACM International Conference on Automated Software Engineering (ASE), 2026 (CCF A)

24. Deployed System: Labeling the Invisible: A Scalable Framework for Labeling Fail-Slow Failures in Cloud Storage Systems

Yongxin Zhao, Yuxin Sun, Shenglin Zhang, Xiang Liu, Jiaqi Luan, Runzhou Wang, Wenwei Gu, Yongqian Sun, Yidan Li, and Dan Pei

In Proceedings of the 25th USENIX Conference on File and Storage Technologies (FAST), 2027 (CCF A)

25. Collaborative Knowledge Distillation and Reinforcement Learning for Automated Ticket Triage in Large-Scale Production Systems

Ruowei Fu, Yang Zhang, Shenglin Zhang, Xin Wu, Wenwei Gu, Feng Wang, Zeyu Che, Xiaozhou Liu, Yongqian Sun, and Yu Zhang

In ACM Transactions on Software Engineering and Methodology (TOSEM), 2026 (CCF A/SCI Q1)

注：*表示通讯作者。

科研项目:

1. 故障应急处置 AIOps研究，阿里巴巴校企合作项目，主持，2026.07-2027.07

2. 基于长上下文感知与多智能体协同的研运一体化(DevOps)风险根因分析研究，CCF-蚂蚁科研基金，主持，2026.08~2027.08

3. 基于Agentic AI的运维效率优化，美团校企合作项目，核心参与，2026.06-2027.06

4. 面向国产异构GPU的故障预警机制研究，阿里巴巴校企合作项目，核心参与，2026.06-2027.06

5. 面向大规模分布式系统的节点劣化判断，美团合作项目，核心参与，2025.06~2026.06

6. AI集群基础设施GPU卡故障预测，字节跳动合作项目，核心参与，2025.05~2026.05

7. 全栈式跨层故障根因定位，华为-港中文软件可靠性联合实验室课题，参与，2023.07~2024.07

8. 基于训练事务流的大模型全链路故障分析，华为-港中文软件可靠性联合实验室课题，参与，2024.07~2025.07

9. 面向微服务领域的场景化根因分析，华为-港中文软件可靠性联合实验室课题，参与，2023.07~2024.07

讲授课程:

1. 本科生课程，计算机网络，2025-2026，秋季学期

2. 研究生课程，软件测试与维护前沿, 2025-2026，秋季学期

社会兼职:

ISSRE 26、QRS 26程序委员会成员

2026 CCF中国软件大会宣传委员会主席

第九届CCF国际智能运维挑战赛技术委员会主席

第八届CCF国际智能运维挑战赛评委

SIGCOMM 26, KDD 26, AAAI 26, ASE 25, ACL 25, ICSE 25, FSE 24, ISSRE 24, DSN 25, ISSTA 24, ESEC/FSE 24, ISSRE 23, DSN 23, ISSRE 22, SRDS 22, ESEC/FSE 22等国际顶尖会议审稿人

TSE, TOSEM, TIFS, TON, TSC, TNNLS, FCS, NN等国际顶尖期刊审稿人