Guangba Yu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Guangba Yu has a total of 86 co-authors. Here are the top co-authors by number of shared publications:
- Pengfei Chen
Sun Yat-Sen University, Guangzhou, China
22 shared publications - Michael R. Lyu
The Chinese University of Hong Kong
16 shared publications - Zilong He
Sun Yat-Sen University, Guangzhou, China
15 shared publications - Zibin Zheng
Sun Yat-Sen University, Guangzhou, China
9 shared publications - Hongyang Chen
School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China
6 shared publications - Xiaoyun Li
School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China
6 shared publications
Latest Publications
- Open Access
- 7 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 4116-4127
OpsLens: Runbook-Free Root Cause Analysis via Multi-agent Collaboration and Tool Management
- 7 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 4116-4127
Open AccessOpsLens: Runbook-Free Root Cause Analysis via Multi-agent Collaboration and Tool Management
- 1 September 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Software Engineering
- Vol. 52 (9) , 2546-2565
CCISolver: End-to-End Detection and Repair of Method-Level Code-Comment Inconsistency
- 1 September 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Software Engineering
- Vol. 52 (9) , 2546-2565
CCISolver: End-to-End Detection and Repair of Method-Level Code-Comment Inconsistency
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 1828-1839
StaR: Stateful Dynamic-Graph Root Cause Analysis through Memory-Enhanced Causality Discovery
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 1828-1839
Open AccessStaR: Stateful Dynamic-Graph Root Cause Analysis through Memory-Enhanced Causality Discovery
- Open Access
- 24 July 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Software Engineering and Methodology
AutoScope: Code Knowledge Enhanced Span-level Sampling for Distributed Tracing
Distributed tracing is essential for observing microservices but incurs prohibitive storage costs. Existing solutions primarily rely on trace-level sampling, which indiscriminately discards entire traces based on probability or tail latency. This coarse-grained approach often loses critical off-the-path anomalies and fails to retain normal baselines required for comparative diagnosis. To address these limitations, we introduce the concept of span-level sampling, a fine-grained paradigm that retains only essential spans rather than full traces. However, we identify a critical challenge in this new approach where naive span retention leads to structural ambiguity, as the removal of intermediate spans disrupts the graph topology and renders the remaining data useless for analysis. To resolve this, we propose AutoScope , a novel framework that leverages static code knowledge to enable structurally safe span-level sampling. AutoScope constructs a Bridged Call Site Control Flow Graph (CSCFG) to map runtime spans to static execution logic. By identifying Dominant Span Sets (DSS), it exploits the “Sample One, Infer All” property to enable aggressive compression while preserving the structural skeleton of every request. Extensive evaluations on two benchmark microservice systems demonstrate that AutoScope achieves an 80.2% storage reduction while maintaining a state-of-the-art faulty span coverage of 98.1%. Furthermore, the reconstructed traces enhance downstream Root Cause Analysis (RCA) tasks, improving the Mean Reciprocal Rank (MRR) by an average of 8.3%.
- 24 July 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Software Engineering and Methodology
Open AccessAutoScope: Code Knowledge Enhanced Span-level Sampling for Distributed Tracing
Distributed tracing is essential for observing microservices but incurs prohibitive storage costs. Existing solutions primarily rely on trace-level sampling, which indiscriminately discards entire traces based on probability or tail latency. This coarse-grained approach often loses critical off-the-path anomalies and fails to retain normal baselines required for comparative diagnosis. To address these limitations, we introduce the concept of span-level sampling, a fine-grained paradigm that retains only essential spans rather than full traces. However, we identify a critical challenge in this new approach where naive span retention leads to structural ambiguity, as the removal of intermediate spans disrupts the graph topology and renders the remaining data useless for analysis. To resolve this, we propose AutoScope , a novel framework that leverages static code knowledge to enable structurally safe span-level sampling. AutoScope constructs a Bridged Call Site Control Flow Graph (CSCFG) to map runtime spans to static execution logic. By identifying Dominant Span Sets (DSS), it exploits the “Sample One, Infer All” property to enable aggressive compression while preserving the structural skeleton of every request. Extensive evaluations on two benchmark microservice systems demonstrate that AutoScope achieves an 80.2% storage reduction while maintaining a state-of-the-art faulty span coverage of 98.1%. Furthermore, the reconstructed traces enhance downstream Root Cause Analysis (RCA) tasks, improving the Mean Reciprocal Rank (MRR) by an average of 8.3%.
- Top Cited PapersOpen Access
- 11 July 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Software Engineering and Methodology
- Vol. 35 (7) , 1-41
Larger Is Not Always Better: Exploring Small Open-Source Language Models in Logging Statement Generation
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.
- 11 July 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Software Engineering and Methodology
- Vol. 35 (7) , 1-41
Top Cited PapersOpen AccessLarger Is Not Always Better: Exploring Small Open-Source Language Models in Logging Statement Generation
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.
- Open Access
- 6 July 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Software Engineering and Methodology
AI-NativeBench: An Open-Source White-Box Agentic Benchmark Suite for AI-Native Systems
The transition from Cloud-Native to AI-Native architectures is fundamentally reshaping software engineering, replacing deterministic microservices with probabilistic agentic services. However, this shift renders traditional black-box evaluation paradigms insufficient: existing benchmarks measure raw model capabilities while remaining blind to system-level execution dynamics. To bridge this gap, we introduce AI-NativeBench, the first application-centric and white-box AI-Native benchmark suite grounded in Model Context Protocol (MCP) and Agent-to-Agent (A2A) standards. By treating agentic spans as first-class citizens within distributed traces, our methodology enables granular analysis of engineering characteristics beyond simple capabilities. Leveraging this benchmark across 21 system variants, we uncover critical engineering realities invisible to traditional metrics: a parameter paradox where lightweight models often surpass flagships in protocol adherence, a pervasive inference dominance that renders protocol overhead secondary, and an expensive failure pattern where self-healing mechanisms paradoxically act as cost multipliers on unviable workflows. This work provides the first systematic evidence to guide the transition from measuring model capability to engineering reliable AI-Native systems. To facilitate reproducibility and further research, we have open-sourced the benchmark and dataset.
- 6 July 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Software Engineering and Methodology
Open AccessAI-NativeBench: An Open-Source White-Box Agentic Benchmark Suite for AI-Native Systems
The transition from Cloud-Native to AI-Native architectures is fundamentally reshaping software engineering, replacing deterministic microservices with probabilistic agentic services. However, this shift renders traditional black-box evaluation paradigms insufficient: existing benchmarks measure raw model capabilities while remaining blind to system-level execution dynamics. To bridge this gap, we introduce AI-NativeBench, the first application-centric and white-box AI-Native benchmark suite grounded in Model Context Protocol (MCP) and Agent-to-Agent (A2A) standards. By treating agentic spans as first-class citizens within distributed traces, our methodology enables granular analysis of engineering characteristics beyond simple capabilities. Leveraging this benchmark across 21 system variants, we uncover critical engineering realities invisible to traditional metrics: a parameter paradox where lightweight models often surpass flagships in protocol adherence, a pervasive inference dominance that renders protocol overhead secondary, and an expensive failure pattern where self-healing mechanisms paradoxically act as cost multipliers on unviable workflows. This work provides the first systematic evidence to guide the transition from measuring model capability to engineering reliable AI-Native systems. To facilitate reproducibility and further research, we have open-sourced the benchmark and dataset.
- Open Access
- 5 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1733-1737
Freezing the Crime Scene: A State Snapshot Paradigm for Reproducible Agentic SRE Evaluation
- 5 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1733-1737
Open AccessFreezing the Crime Scene: A State Snapshot Paradigm for Reproducible Agentic SRE Evaluation
- Open Access
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 2925-2937
PreServe: Intelligent Management for LMaaS Systems via Hierarchical Prediction
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 2925-2937
Open AccessPreServe: Intelligent Management for LMaaS Systems via Hierarchical Prediction
- Open Access
- 10 March 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Autonomous and Adaptive Systems
- Vol. 21 (1) , 1-29
Fine-grained Tracing for Performance Anomaly Diagnosis of Serverless Functions
Serverless function compositions subject to unpredictable faults are challenging to evaluate for root cause analysis. Even though distributed tracing provides observations at multiple levels of granularity for troubleshooting, excessive code instrumentation increases the tracing overheads in terms of both computation and storage. Therefore, developers face the challenge of where and how to instrument serverless functions to maximize the likelihood of locating faults based on tracing data while minimizing tracing overhead and costs. In this article, we propose a methodology to instrument an application with code-level tracing to infer the location of faults, taking into account constraints in terms of the maximum cost of the instrumentation and testing. We encode the tracing probe placement based on the control flow graph of the application and devise heuristics-based tracing data collection strategies to relate possible probe placements with their ability to locate a fault. Then we train novelty detection models to identify the internal anomalies and present an enhanced global search algorithm that automatically computes a probe placement with optimal fault localization ability versus cost. Experimental results show high performance in locating single and multiple faults with over 90% recall score for up to 15% latency anomalies, with minimal instrumentation overhead.
- 10 March 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Autonomous and Adaptive Systems
- Vol. 21 (1) , 1-29
Open AccessFine-grained Tracing for Performance Anomaly Diagnosis of Serverless Functions
Serverless function compositions subject to unpredictable faults are challenging to evaluate for root cause analysis. Even though distributed tracing provides observations at multiple levels of granularity for troubleshooting, excessive code instrumentation increases the tracing overheads in terms of both computation and storage. Therefore, developers face the challenge of where and how to instrument serverless functions to maximize the likelihood of locating faults based on tracing data while minimizing tracing overhead and costs. In this article, we propose a methodology to instrument an application with code-level tracing to infer the location of faults, taking into account constraints in terms of the maximum cost of the instrumentation and testing. We encode the tracing probe placement based on the control flow graph of the application and devise heuristics-based tracing data collection strategies to relate possible probe placements with their ability to locate a fault. Then we train novelty detection models to identify the internal anomalies and present an enhanced global search algorithm that automatically computes a probe placement with optimal fault localization ability versus cost. Experimental results show high performance in locating single and multiple faults with over 90% recall score for up to 15% latency anomalies, with minimal instrumentation overhead.
- Open Access
- 3 March 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Storage
- Vol. 22 (4) , 1-35
EFRC is Adapted to Access-rate Imbalance: A Class of Efficient and Fair Replacement Algorithms for Cache Sharing
Co-located workloads demand fine-grained management of caching control for enhanced deterministic performance. Traditionally, minimizing cache interference has relied on hardware mechanisms that offer coarse cache resource allocation across cores or the last-level cache. More often than not, existing cache replacement algorithms aim to optimize cache hit efficiency depending on single workload access characteristics. In this paper, we propose a series of replacement algorithms for multi-workload shared caches, radically enhancing the deterministic performance of co-located workloads. We devise a class of replacement algorithms for cache sharing, referred to as Efficient and Fair Replacement Cache or EFRC. To strick a balance between performance and complexity, we divide the class of algorithms into Type I and Type II according to the data access characteristics. The common idea of our EFRC-I and EFRC-II algorithms is to judiciously adjust resources for a diversity of workloads or data characteristics online by triggering various resource allocation policies through a corresponding ghost cache preceptor. Our extensive experiments unveil that the EFRC-I and EFRC-II algorithms exhibit a handful of advantages. Firstly, the algorithms support multiple workloads sharing cache – and are compatible with single workload scenarios. Secondly, the cache-hit performance of our proposed EFRC-I and EFRC-II algorithms is superior to that of the existing ARC, LIRS, CACHEUS, and SIEVE algorithms in multi-workload shared caches. Importantly, our technique enhances the fairness of co-located workloads. In particular, when access rates of co-located workloads are imbalanced, our method demonstrates clear superiority over the baseline and the aforementioned state-of-the-art algorithms.
- 3 March 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Storage
- Vol. 22 (4) , 1-35
Open AccessEFRC is Adapted to Access-rate Imbalance: A Class of Efficient and Fair Replacement Algorithms for Cache Sharing
Co-located workloads demand fine-grained management of caching control for enhanced deterministic performance. Traditionally, minimizing cache interference has relied on hardware mechanisms that offer coarse cache resource allocation across cores or the last-level cache. More often than not, existing cache replacement algorithms aim to optimize cache hit efficiency depending on single workload access characteristics. In this paper, we propose a series of replacement algorithms for multi-workload shared caches, radically enhancing the deterministic performance of co-located workloads. We devise a class of replacement algorithms for cache sharing, referred to as Efficient and Fair Replacement Cache or EFRC. To strick a balance between performance and complexity, we divide the class of algorithms into Type I and Type II according to the data access characteristics. The common idea of our EFRC-I and EFRC-II algorithms is to judiciously adjust resources for a diversity of workloads or data characteristics online by triggering various resource allocation policies through a corresponding ghost cache preceptor. Our extensive experiments unveil that the EFRC-I and EFRC-II algorithms exhibit a handful of advantages. Firstly, the algorithms support multiple workloads sharing cache – and are compatible with single workload scenarios. Secondly, the cache-hit performance of our proposed EFRC-I and EFRC-II algorithms is superior to that of the existing ARC, LIRS, CACHEUS, and SIEVE algorithms in multi-workload shared caches. Importantly, our technique enhances the fairness of co-located workloads. In particular, when access rates of co-located workloads are imbalanced, our method demonstrates clear superiority over the baseline and the aforementioned state-of-the-art algorithms.