Chenyu Zhao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Chenyu Zhao has a total of 35 co-authors. Here are the top co-authors by number of shared publications:
- Dan Pei
Tsinghua University
6 shared publications - Shenglin Zhang
Nankai University
6 shared publications - Yongqian Sun
Nankai University, Tianjin, China
6 shared publications - Minghua Ma
Microsoft, Redmond, Washington, USA
4 shared publications - Chetan Bansal
Microsoft, Redmond, Washington, USA
3 shared publications - Saravan Rajmohan
Microsoft, Redmond, Washington, USA
3 shared publications
Latest Publications
- Open Access
- 4 November 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Software Engineering and Methodology
- Vol. 35 (11) , 1-39
Can Language Models Go beyond Coding? Assessing the Capability of Language Models to Build Real-World Systems
Large language models (LLMs) have shown growing potential in software engineering, yet few benchmarks evaluate their ability to repair software during migration across instruction set architectures (ISAs). Cross-ISA migration, such as between x86_64 and aarch64 , requires handling complex dependencies, heterogeneous toolchains, and long build logs while ensuring executable verification. To address this challenge, we present Build-bench (Homepage: https://aiops-lab-nku.github.io/Build-bench/ , Code at https://github.com/zcyyc/Build-bench ), an end-to-end benchmark that systematically evaluates the capability of LLMs to repair build failures in cross-ISA settings. Build-bench collects 268 real-world failed packages and integrates auxiliary tools including Structure Extraction , File Content Extraction , Content Modification , and Build Verification to support autonomous, tool-augmented reasoning. The repair process operates in an iterative loop where, upon failure, the model receives updated build logs and previous repair outcomes to refine subsequent attempts. Through a comparative evaluation across the studied models, Build-bench reveals that current models achieve a maximum build success rate of 63.19% and tool usage patterns differ significantly across models. By coupling real build environments with verifiable outcomes, Build-bench establishes the first architecture-aware benchmark for studying LLM-based software build and repair.
- 4 November 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Software Engineering and Methodology
- Vol. 35 (11) , 1-39
Open AccessCan Language Models Go beyond Coding? Assessing the Capability of Language Models to Build Real-World Systems
Large language models (LLMs) have shown growing potential in software engineering, yet few benchmarks evaluate their ability to repair software during migration across instruction set architectures (ISAs). Cross-ISA migration, such as between x86_64 and aarch64 , requires handling complex dependencies, heterogeneous toolchains, and long build logs while ensuring executable verification. To address this challenge, we present Build-bench (Homepage: https://aiops-lab-nku.github.io/Build-bench/ , Code at https://github.com/zcyyc/Build-bench ), an end-to-end benchmark that systematically evaluates the capability of LLMs to repair build failures in cross-ISA settings. Build-bench collects 268 real-world failed packages and integrates auxiliary tools including Structure Extraction , File Content Extraction , Content Modification , and Build Verification to support autonomous, tool-augmented reasoning. The repair process operates in an iterative loop where, upon failure, the model receives updated build logs and previous repair outcomes to refine subsequent attempts. Through a comparative evaluation across the studied models, Build-bench reveals that current models achieve a maximum build success rate of 63.19% and tool usage patterns differ significantly across models. By coupling real build environments with verifiable outcomes, Build-bench establishes the first architecture-aware benchmark for studying LLM-based software build and repair.
- Open Access
- 7 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 4006-4017
Debugging the Debuggers: Failure-Anchored Structured Recovery for Software Engineering Agents
- 7 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 4006-4017
Open AccessDebugging the Debuggers: Failure-Anchored Structured Recovery for Software Engineering Agents
- Open Access
- 1 October 2026
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Software Engineering
- Vol. 3 (ISSTA) , 4653-4673
EvidenT: An Evidence-Preserving Framework for Iterative System-Level Package Repair
Frequent toolchain updates and the expanding diversity of instruction set architectures (ISAs) have made large-scale system-level software package repair a critical task. Diagnosing and repairing build failures remains challenging due to heterogeneous failure evidence, complex dependency constraints, and architecture-specific build conventions. While recent LLM-based repair methods have shown promise for project-level source code fixes, they struggle with system-level repair where failures involve multi-language artifacts (e.g., build recipes, scripts, and source archives) and require iterative validation through external build services. In this paper, we first conduct a systematic empirical study of real-world system-level build failures. Our findings reveal that 72% of successful repairs primarily involve adjustments to build configurations, dependencies, or environment settings rather than isolated source-code modifications, suggesting that effective repair must prioritize packaging logic and iterative feedback. Motivated by these insights, we propose EvidenT, an evidence-preserving repair framework that decouples iteration-aware evidence management from tool execution. EvidenT comprises (1) an external Build Service for reproducible build execution and feedback; (2) an Evidence-Preserving Repair Controller that performs cross-modal fusion of repair history, knowledge context, and build artifacts; and (3) an automated Repair Orchestrator that executes a suite of modular tools for failure localization and system-level repair actions within a closed-loop validation environment. We evaluate EvidenT on a benchmark of 219 real-world RISC-V package build failures. EvidenT successfully repairs 118 packages (53.88%), substantially outperforming state-of-the-art agentic baselines (20.55%) and direct LLM-based repair (1.83%). To demonstrate its architectural generality, we extend EvidenT to other ISAs by updating only ISA-specific knowledge context. In preliminary experiments, it achieves success rates of 41.77% on aarch64 and 46.99% on x86_64, showcasing its robustness across diverse hardware ecosystems.
- 1 October 2026
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Software Engineering
- Vol. 3 (ISSTA) , 4653-4673
Open AccessEvidenT: An Evidence-Preserving Framework for Iterative System-Level Package Repair
Frequent toolchain updates and the expanding diversity of instruction set architectures (ISAs) have made large-scale system-level software package repair a critical task. Diagnosing and repairing build failures remains challenging due to heterogeneous failure evidence, complex dependency constraints, and architecture-specific build conventions. While recent LLM-based repair methods have shown promise for project-level source code fixes, they struggle with system-level repair where failures involve multi-language artifacts (e.g., build recipes, scripts, and source archives) and require iterative validation through external build services. In this paper, we first conduct a systematic empirical study of real-world system-level build failures. Our findings reveal that 72% of successful repairs primarily involve adjustments to build configurations, dependencies, or environment settings rather than isolated source-code modifications, suggesting that effective repair must prioritize packaging logic and iterative feedback. Motivated by these insights, we propose EvidenT, an evidence-preserving repair framework that decouples iteration-aware evidence management from tool execution. EvidenT comprises (1) an external Build Service for reproducible build execution and feedback; (2) an Evidence-Preserving Repair Controller that performs cross-modal fusion of repair history, knowledge context, and build artifacts; and (3) an automated Repair Orchestrator that executes a suite of modular tools for failure localization and system-level repair actions within a closed-loop validation environment. We evaluate EvidenT on a benchmark of 219 real-world RISC-V package build failures. EvidenT successfully repairs 118 packages (53.88%), substantially outperforming state-of-the-art agentic baselines (20.55%) and direct LLM-based repair (1.83%). To demonstrate its architectural generality, we extend EvidenT to other ISAs by updating only ISA-specific knowledge context. In preliminary experiments, it achieves success rates of 41.77% on aarch64 and 46.99% on x86_64, showcasing its robustness across diverse hardware ecosystems.
- Open Access
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 4839-4850
FlowXpert: Expertizing Troubleshooting Workflow Orchestration with Knowledge Base and Multi-Agent Coevolution
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 4839-4850
Open AccessFlowXpert: Expertizing Troubleshooting Workflow Orchestration with Knowledge Base and Multi-Agent Coevolution
- Open Access
- 23 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 215-226
LLM-Augmented Ticket Aggregation for Low-cost Mobile OS Defect Resolution
- 23 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 215-226
Open AccessLLM-Augmented Ticket Aggregation for Low-cost Mobile OS Defect Resolution
- Top Cited PapersOpen Access
- 4 August 2023
- Published by Association for Computing Machinery (ACM)
- p. 5639-5649
Robust Multimodal Failure Detection for Microservice Systems
Proactive failure detection of instances is vitally essential to microservice systems because an instance failure can propagate to the whole system and degrade the system's performance. Over the years, many single-modal (i.e., metrics, logs, or traces) databased anomaly detection methods have been proposed. However, they tend to miss a large number of failures and generate numerous false alarms because they ignore the correlation of multimodal data. In this work, we propose AnoFusion, an unsupervised failure detection approach, to proactively detect instance failures through multimodal data for microservice systems. It applies a Graph Transformer Network (GTN) to learn the correlation of the heterogeneous multimodal data and integrates a Graph Attention Network (GAT) with Gated Recurrent Unit (GRU) to address the challenges introduced by dynamically changing multimodal data. We evaluate the performance of AnoFusion through two datasets, demonstrating that it achieves the F1-score of 0.857 and 0.922, respectively, outperforming the state-of-the-art failure detection approaches.
- 4 August 2023
- Published by Association for Computing Machinery (ACM)
- p. 5639-5649
Top Cited PapersOpen AccessRobust Multimodal Failure Detection for Microservice Systems
Proactive failure detection of instances is vitally essential to microservice systems because an instance failure can propagate to the whole system and degrade the system's performance. Over the years, many single-modal (i.e., metrics, logs, or traces) databased anomaly detection methods have been proposed. However, they tend to miss a large number of failures and generate numerous false alarms because they ignore the correlation of multimodal data. In this work, we propose AnoFusion, an unsupervised failure detection approach, to proactively detect instance failures through multimodal data for microservice systems. It applies a Graph Transformer Network (GTN) to learn the correlation of the heterogeneous multimodal data and integrates a Graph Attention Network (GAT) with Gated Recurrent Unit (GRU) to address the challenges introduced by dynamically changing multimodal data. We evaluate the performance of AnoFusion through two datasets, demonstrating that it achieves the F1-score of 0.857 and 0.922, respectively, outperforming the state-of-the-art failure detection approaches.