Jiayi Mao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Jiayi Mao has a total of 25 co-authors. Here are the top co-authors by number of shared publications:
- Lei Deng
School of Computer Science and Engineering, Central South University , Changsha 410083
2 shared publications - Chaoyun Zhang
Microsoft, Beijing, China
1 shared publication - Dongmei Zhang
Microsoft Research Asia, Beijing, China
1 shared publication Hanle Zheng
Center for Brain Inspired Computing Research, Department of Precision Instrument, Tsinghua University, Beijing, 100084, China
1 shared publication- Hanle Zheng
Center for Brain Inspired Computing Research, Department of Precision Instrument, Tsinghua University, Beijing, China
1 shared publication Hanxiao Fan
Center for Brain Inspired Computing Research, Department of Precision Instrument, Tsinghua University, Beijing, 100084, China
1 shared publication
Latest Publications
- Open Access
- 30 June 2026
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Software Engineering
- Vol. 3 (FSE) , 3070-3092
StepFly: Agentic Troubleshooting Guide Automation for Incident Diagnosis
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 offer promise for automating incident management tasks, existing LLM-based solutions lack specialized support for several key challenges, including managing TSG quality issues, interpreting complex control flow, handling data-intensive queries, and exploiting execution parallelism. We first conducted an empirical study on 92 real-world TSGs, and, guided by our findings, we present , a novel end-to-end agentic framework for troubleshooting guide automation. Our approach features a three-stage workflow: the first stage provides a comprehensive guide together with a tool, TSG Mentor, to assist site reliability engineers (SREs) in improving TSG quality; the second stage performs offline preprocessing using LLMs to extract structured execution directed acyclic graphs (DAGs) from unstructured TSGs and to create dedicated Query Preparation Plugins (QPPs); and the third stage executes online using a DAG-guided scheduler-executor framework with a memory system to ensure correct workflow and support parallel execution of independent steps. Our empirical evaluation on a collection of real-world TSGs and incidents demonstrates that achieves a ∼94% success rate on GPT-4.1, outperforming baselines with less time and token consumption. Furthermore, it achieves a remarkable execution time reduction of 32.9% to 70.4% for parallelizable TSGs. Our code and sample data are publicly available at https://github.com/microsoft/StepFly.
- 30 June 2026
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Software Engineering
- Vol. 3 (FSE) , 3070-3092
Open AccessStepFly: Agentic Troubleshooting Guide Automation for Incident Diagnosis
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 offer promise for automating incident management tasks, existing LLM-based solutions lack specialized support for several key challenges, including managing TSG quality issues, interpreting complex control flow, handling data-intensive queries, and exploiting execution parallelism. We first conducted an empirical study on 92 real-world TSGs, and, guided by our findings, we present , a novel end-to-end agentic framework for troubleshooting guide automation. Our approach features a three-stage workflow: the first stage provides a comprehensive guide together with a tool, TSG Mentor, to assist site reliability engineers (SREs) in improving TSG quality; the second stage performs offline preprocessing using LLMs to extract structured execution directed acyclic graphs (DAGs) from unstructured TSGs and to create dedicated Query Preparation Plugins (QPPs); and the third stage executes online using a DAG-guided scheduler-executor framework with a memory system to ensure correct workflow and support parallel execution of independent steps. Our empirical evaluation on a collection of real-world TSGs and incidents demonstrates that achieves a ∼94% success rate on GPT-4.1, outperforming baselines with less time and token consumption. Furthermore, it achieves a remarkable execution time reduction of 32.9% to 70.4% for parallelizable TSGs. Our code and sample data are publicly available at https://github.com/microsoft/StepFly.
- 8 January 2026
- Published by Elsevier in Neural Networks
- Vol. 198, 108558
Temporal local attention with adaptive decoding: Enhancing spiking neural networks for temporal computing applications
- 8 January 2026
- Published by Elsevier in Neural Networks
- Vol. 198, 108558
Temporal local attention with adaptive decoding: Enhancing spiking neural networks for temporal computing applications
- 9 October 2025
- Published by Elsevier in Neural Networks
- Vol. 194, 108191
Adaptive dendritic plasticity in brain-inspired dynamic neural networks for enhanced multi-timescale feature extraction
- 9 October 2025
- Published by Elsevier in Neural Networks
- Vol. 194, 108191
Adaptive dendritic plasticity in brain-inspired dynamic neural networks for enhanced multi-timescale feature extraction