Wenwei Gu

Wenwei Gu

Auto-generated profile, based on publicly available information

Wenwei Gu

Nankai University, Tianjin, China

Research Focus & Metrics

Academic Career Length

26Years (2001-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
11 December 2025 in ACM Transactions on Software Engineering and Methodology
Verified
Journal Article
Open access
RZRenyi Zhong
Renyi Zhong
YLYichen Li
Yichen Li
JKJinxi Kuang
Jinxi Kuang
WGWenwei Gu
Wenwei Gu
YHYintong Huo
Yintong Huo
MLMichael R. Lyu
Michael R. Lyu
Developers write logging statements to monitor software runtime behaviors and system state. However, poorly constructed or misleading log messages can inadvertently obfuscate actual program execution patterns, thereby impeding effective software maintenance. Existing research on analyzing issues within logging statements is limited, primarily focusing on detecting a singular type of defect and relying on manual intervention for fixes rather than automated solutions. To address the limitation, we initiate a systematic study that pinpoints four specific types of defects in logging statements (i.e., statement code inconsistency, static dynamic inconsistency, temporal relation inconsistency, and readability issues) through the analysis of real-world log-centric changes. We then propose LogUpdater , a two-stage framework for automatically detecting and updating logging statements for these specific defects. In the offline stage, LogUpdater constructs a similarity-based classifier on a set of synthetic defective logging statements to identify specific defect types. During the online testing phase, this classifier first evaluates logging statements in a given code snippet to determine the necessity and type of improvements required. Then, LogUpdater constructs type-aware prompts from historical logging update changes for an LLM-based recommendation framework to suggest updates addressing these specific defects. We evaluate the effectiveness of LogUpdater on a dataset containing real-world logging changes, a synthetic dataset, and a new real-world project dataset. The results indicate that our approach is highly effective in detecting logging defects, achieving an F1-score of 0.625. Additionally, it exhibits significant improvements in suggesting precise static text and dynamic variables, with enhancements of 48.12% and 24.90%, respectively. Furthermore, LogUpdater achieves a 61.49% success rate in recommending correct updates on new real-world projects. We reported 40 problematic logging statements and their fixes to GitHub via pull requests, resulting in 25 changes confirmed and merged across 11 different projects.

23 February 2025 in ACM Transactions on Software Engineering and Methodology
Verified
Journal Article
Open access
WGWenwei Gu
Wenwei Gu
JLJinyang Liu
Jinyang Liu
ZCZhuangbin Chen
Zhuangbin Chen
JZJianping Zhang
Jianping Zhang
YSYuxin Su
Yuxin Su
MLMichael R. Lyu
Michael R. Lyu
Cloud systems, typically comprised of various components (e.g., microservices), are susceptible to performance issues, which may cause service-level agreement violations and financial losses. Identifying performance issues is thus of paramount importance for cloud vendors. In current practice, crucial metrics, i.e., Key Performance Indicators (KPIs), are monitored periodically to provide insight into the operational status of components. Identifying performance issues is often formulated as an anomaly detection problem, which is tackled by analyzing each metric independently. However, this approach overlooks the complex dependencies existing among cloud components. Some graph neural network-based methods take both temporal and relational information into account; however, the correlation violations in the metrics that serve as indicators of underlying performance issues are difficult for them to identify. Furthermore, a large volume of components in a cloud system results in a vast array of noisy metrics. This complexity renders it impractical for engineers to fully comprehend the correlations, making it challenging to identify performance issues accurately. To address these limitations, we propose Identifying Performance Issues based on Relational-Temporal Features (ISOLATE), a learning-based approach that leverages both the relational and temporal features of metrics to identify performance issues. In particular, it adopts a graph neural network with attention to characterizing the relations among metrics and extracts long-term and multi-scale temporal patterns using a GRU and a convolution network, respectively. The learned graph attention weights can be further used to localize the correlation-violated metrics. Moreover, to relieve the impact of noisy data, ISOLATE utilizes a Positive Unlabeled (PU) Learning strategy that tags pseudo-labels based on a small portion of confirmed negative examples. Extensive evaluation on both public and industrial datasets shows that ISOLATE outperforms all baseline models with 0.945 F1 score and 0.920 Hit rate@3. The ablation study also proves the effectiveness of the relational-temporal features and the PU-Learning strategy. Furthermore, we share the success stories of leveraging ISOLATE to identify performance issues in Huawei Cloud, which demonstrates its superiority in practice.

11 July 2026 in ACM Transactions on Software Engineering and Methodology
Verified
Journal Article
Open access
RZRenyi Zhong
Renyi Zhong
YLYichen Li
Yichen Li
GYGuangba Yu
Guangba Yu
WGWenwei Gu
Wenwei Gu
JKJinxi Kuang
Jinxi Kuang
MLMichael R. Lyu
Michael R. Lyu
Developers use logging statements to create logs that document system behavior and aid in software maintenance. As such, high-quality logging is essential for effective maintenance; however, manual logging often leads to errors and inconsistency. Recent methods emphasize using Large Language Models (LLMs) for automated logging statement generation, but these present privacy and resource issues, hindering their suitability for enterprise use. This article presents the first large-scale empirical study evaluating Small Open-Source Language Models (SOLMs) for automated logging statement generation. We evaluate four prominent SOLMs using various prompt strategies and parameter-efficient fine-tuning techniques, such as Low-Rank Adaptation (LoRA) and Retrieval-Augmented Generation (RAG). Our results show that fine-tuned SOLMs with LoRA and RAG prompts, particularly Qwen2.5-coder-14B, outperform existing tools and LLM baselines (e.g., Claude3.7 sonnet and GPT4o) in predicting logging locations and generating high-quality statements, with robust generalization across diverse repositories. These findings highlight SOLMs as a privacy-preserving, efficient alternative for automated logging.

12 April 2026
Verified
Conference Paper
Open access
YZYongxin Zhao
Yongxin Zhao
Shenglin ZhangShenglin Zhang
Shenglin Zhang
YSYuxin Sun
Yuxin Sun
WGWenwei Gu
Wenwei Gu
YSYongqian Sun
Yongqian Sun
DPDan Pei
Dan Pei

12 April 2026
Verified
Conference Paper
Open access
RZRenyi Zhong
Renyi Zhong
YHYintong Huo
Yintong Huo
WGWenwei Gu
Wenwei Gu
YLYichen Li
Yichen Li
MLMichael R. Lyu
Michael R. Lyu
Software logging is critical for system observability, yet developers face a dual crisis of costly overlogging and risky underlogging. Existing automated logging tools often overlook the fundamental whether-to-log decision and struggle with the composite nature of logging. In this paper, we propose AutoLogger, a novel hybrid framework that addresses the complete the end-to-end logging pipeline. AutoLogger first employs a fine-tuned classifier, the Judger, to accurately determine if a method requires new logging statements. If logging is needed, a multi-agent system is activated. The system includes specialized agents: a Locator dedicated to determining where to log, and a Generator focused on what to log. These agents work together, utilizing our designed program analysis and retrieval tools. We evaluate AutoLogger on a large corpus from three mature open-source projects against state-of-the-art baselines. Our results show that AutoLogger achieves 96.63% F1-score on the crucial whether-to-log decision. In an end-to-end setting, AutoLogger improves the overall quality of generated logging statements by 16.13% over the strongest baseline, as measured by an LLM-as-a-judge score. We also demonstrate that our framework is generalizable, consistently boosting the performance of various backbone LLMs.

31 August 2026 in ACM Transactions on Software Engineering and Methodology
Verified
Journal Article
Open access
BSBinpeng Shi
Binpeng Shi
Shenglin ZhangShenglin Zhang
Shenglin Zhang
JWJingya Wang
Jingya Wang
BHBowen Hao
Bowen Hao
MSMinyi Shao
Minyi Shao
DPDan Pei
Dan Pei
AIOps (Artificial Intelligence for IT Operations) has emerged as a key strategy for operating large-scale systems. Meanwhile, the Transformer architecture, renowned for its strong performance and potential, is driving advances in AIOps. However, prior reviews leave gaps in explaining why Transformers trigger a major shift in academia and industry, with limited coverage of multimodal data (logs, metrics, events), insufficient analysis of structural and methodological connections between Transformers and AIOps, fragmented views of capabilities, and a lack of consolidated evaluation strategies. To bridge these gaps, our work decomposes “Why Transformers” into three questions. First, we review what roles Transformers assume in AIOps across 70 representative papers, using a structured taxonomy that proceeds sequentially from data to targets, principles, and approaches, which present an evolutionary trajectory of role changes. Then, to explain why Transformers excel, we introduce a capability framework comprising two basic and four advanced capabilities. As for how to evaluate Transformers in AIOps, we consolidate evaluation resources and strategies, including offline datasets, standardized questions, and real-time simulations. Furthermore, probable best practices are distilled, offering actionable guidance for real-world adoption. These explorations aim to clarify the internal rationale and unlock the practical value of Transformers in AIOps.