TOSEM 2026CCF-A
A Survey on Failure Analysis and Fault Injection in AI Systems
In ACM Transactions on Software Engineering and Methodology
What I work on
Publications.
Research on reliability and optimization in cloud and AI systems.
* Equal contribution · ✉️ Corresponding author
2026
TSE 2026CCF-A
CCISolver: End-to-End Detection and Repair of Method-Level Code-Comment Inconsistency
In IEEE Transactions on Software Engineering.
TOSEM 2026CCF-A
Larger Is Not Always Better: Exploring Small Open-source Language Models in Logging Statement Generation
In ACM Transactions on Software Engineering and Methodology.
TOSEM 2026CCF-A
AutoScope: Code Knowledge Enhanced Span-level Sampling for Distributed Tracing
In ACM Transactions on Software Engineering and Methodology.
TOSEM 2026CCF-A
AI-NativeBench: An Open-Source White-Box Agentic Benchmark Suite for AI-Native Systems
In ACM Transactions on Software Engineering and Methodology.
ACM TOS 2026
EFRC is Adapted to Access-rate Imbalance: A Class of Efficient and Fair Replacement Algorithms for Cache Sharing
In ACM Transactions on Storage.
ACM TAAS 2026CCF-B
KDD 2026CCF-A
JSS 2026CCF-B
J. Software (CN) 2026CCF-A
面向大规模在线系统的故障根因变更识别 (Root Cause Change Identification for Failures in Large-scale Online System; in Chinese)
In Journal of Software (Chinese).
ICSE 2026CCF-A
PreServe: Intelligent Management for LMaaS Systems via Hierarchical Prediction
In IEEE/ACM International Conference on Software Engineering.
ACM SIGSOFT Distinguished Paper Award
FSE Companion (IVR) 2026
Freezing the Crime Scene: A State Snapshot Paradigm for Reproducible Agentic SRE Evaluation
In ACM International Conference on the Foundations of Software Engineering, Companion Proceedings (Ideas, Visions and Reflections).
EMSE 2026CCF-B
KPIRoot+: An efficient integrated framework for anomaly detection and root cause analysis in large-scale cloud systems
In Empirical Software Engineering.
DSN 2026CCF-B
LLMGuard: Multi-Agent Fault Diagnosis for Reliable Language-Model-as-a-Service
In IEEE/IFIP International Conference on Dependable Systems and Networks.
ASE 2026CCF-A
OpsLens: Runbook-Free Root Cause Analysis via Multi-agent Collaboration and Tool Management
In IEEE/ACM International Conference on Automated Software Engineering.
arXiv 2026
Why Does the LLM Stop Computing: An Empirical Study of User-Reported Failures in Open-Source LLMs
arXiv.
arXiv 2026
Cloud-OpsBench: A Reproducible Benchmark for Agentic Root Cause Analysis in Cloud Systems
arXiv.
2025
ASE 2025CCF-A
iKnow: an Intent-Guided Chatbot for Cloud Operations with Retrieval-Augmented Generation
In 40th IEEE/ACM International Conference on Automated Software Engineering
ACM SIGSOFT Distinguished Paper Award
ASE 2025CCF-A
AlertGuardian: Intelligent Alert Life-Cycle Management for Large-scale Cloud Systems
In 40th IEEE/ACM International Conference on Automated Software Engineering
- Cloud systems
- Alert management
IEEE/ACM ToN 2025CCF-A
NetScope: Fault Localization in Programmable Networking Systems With Low-Cost In-Band Network Telemetry and In-Network Detection
In IEEE Transactions on Networking
TSE 2025CCF-A
Subgraphs as First-Class Citizens in Incident Management for Large-Scale Online Systems: An Evolution-Aware Framework
In IEEE Transactions Software Engineering
IWQoS 2025CCF-B
Causelens: Causality-Based Interpretable Root Cause Analysis for Microservice Systems
In IEEE/ACM International Symposium on Quality of Service
DSN 2025CCF-B
LLMPrism: Black-box Performance Diagnosis for Production LLM Training Platforms
In 55th Annual IEEE/IFIP International Conference on Dependable Systems and Networks
Internetware 2025CCF-C
Take Kernel Stack Overhead Out: eBPF-Enhanced Network Acceleration for Distributed Training within Ethernet
In 16th International Conference on Internetware.
FSE 2025CCF-A
L4: Diagnosing Large-scale LLM Training Failures via Automated Log Analysis
In 33nd ACM International Conference on the Foundations of Software Engineering.
- LLM training
- Failure diagnosis
- Log analysis
ICSE 2025CCF-A
COCA: Generative Root Cause Analysis for Distributed Systems with Code Knowledge
In 47th IEEE/ACM International Conference on Software Engineering
- Distributed systems
- Root cause analysis
SANER 2025CCF-B
Conan: Uncover Consensus Issues in Distributed Databases Using Fuzzing-Driven Fault Injection
In IEEE International Conference on Software Analysis, Evolution and Reengineering
ASPLOS 2025CCF-A
Mint: Cost-Efficient Tracing with All Requests Collection via Commonality and Variability Analysis
In 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems.
arXiv 2025
2024
ASE 2024CCF-A
FaaSConf: QoS-aware Hybrid Resources Configuration for Serverless Workflows
In 39th IEEE/ACM International Conference on Automated Software Engineering.
ISSRE 2024CCF-B
FaaSRCA: Full Lifecycle Root Cause Analysis for Serverless Applications
In 35th IEEE International Symposium on Software Reliability Engineering.
Internetware 2024CCF-C
CTuner: Automatic NoSQL Database Tuning with Causal Reinforcement Learning
In 15th Asia-Pacific Symposium on Internetware.
TDSC 2024CCF-A
MicroFI: Non-Intrusive and Prioritized Request-Level Fault Injection for Microservice Applications
In IEEE Transactions on Dependable and Secure Computing
FSE 2024CCF-A
TraStrainer: Adaptive Sampling for Distributed Traces with System Runtime State
In 32nd ACM International Conference on the Foundations of Software Engineering.
ACM SIGSOFT Distinguished Paper Award
FSE 2024CCF-A
JNCA 2024CCF-C
2023
FSE 2023CCF-A
Nezha: Interpretable Fine-Grained Root Causes Analysis for Microservices on Multi-modal Observability Data
In 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering
FSE 2023CCF-A
DiagConfig: Configuration Diagnosis of Performance Violations in Configurable Software Systems
In 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering
ICPP 2023CCF-B
MARS: Fault Localization in Programmable Networking Systems with Low-cost In-Band Network Telemetry
In 32nd International Conference on Parallel Processing
ICPP 2023CCF-B
DeepPower: Deep Reinforcement Learning based Power Management for Latency Critical Applications in Multi-core Systems
In 32nd International Conference on Parallel Processing
ICSE 2023CCF-A
LogReducer: Identify and Reduce Log Hotspots in Kernel on the Fly
In 45th IEEE/ACM International Conference on Software Engineering
TSC 2023CCF-A
FaaSDeliver: Cost-Efficient and QoS-Aware Function Delivery in Computing Continuum
In IEEE Transaction on Service Computing
TDSC 2023CCF-A
SwissLog: Robust Anomaly Detection and Localization for Interleaved Unstructured Logs
In IEEE Transactions on Dependable and Secure Computing
JSEP 2023CCF-B
TraceRank: Abnormal service localization with dis-aggregated end-to-end tracing data in cloud native systems
In Journal of Software Evolution and Process
IEEE TNNLS 2023CCF-B
A Spatiotemporal Deep Learning Approach for Unsupervised Anomaly Detection in Cloud Systems
In IEEE Transactions on Neural Networks and Learning Systems
ESI Highly Cited Paper
J. Software (CN) 2023CCF-A
面向Java微服务系统的透明请求追踪及采样方法 (Transparent Request Tracing and Sampling for Java Microservice Systems; in Chinese)
In Journal of Software (Chinese).
2022
ICSOC 2022CCF-B
MicroSketch: Lightweight and Adaptive Sketch Based Performance Issue Detection and Localization in Microservice Systems
In 20th International Conference on Service-Oriented Computing
ISSRE 2022CCF-B
Going through the Life Cycle of Faults in Clouds: Guidelines on Fault Handling
In 33rd IEEE International Symposium on Software Reliability Engineering
ASE 2022CCF-A
Graph based Incident Extraction and Diagnosis in Large-Scale Online Systems
In 37th IEEE/ACM International Conference on Automated Software Engineering
ICWS 2022CCF-B
TS-InvarNet: Anomaly Detection and Localization based on Tempo-spatial KPI Invariants in Distributed Services
In Proceeidings of 2022 IEEE International Conference on Web Services
IEEE TCC 2022
Microscaler: Cost-Effective Scaling for Microservice Applications in the Cloud With an Online Learning Approach
In IEEE Transaction on Cloud Computing
2021
ICWS 2021CCF-B
Sieve: Attention-based Sampling of End-to-End Trace Data in Distributed Microservice Systems
In Proceeidings of 2021 IEEE International Conference on Web Services
CCGrid 2021CCF-C
T-Rank: A Lightweight Spectrum based Fault Localization Approach for Microservice Systems
In Proceedings of 2021 IEEE/ACM 21st International Symposium on Cluster, Cloud and Internet Computing
CloudIntelligence 2021
Kmon: An In-kernel Transparent Monitoring System for Microservice Systems with eBPF
In Proceedings of 2021 IEEE/ACM International Workshop on Cloud Intelligence
WWW 2021CCF-A
MicroRank: End-to-End Latency Issue Localization with Extended Spectrum Analysis in Microservice Environments
In Proceedings of the Web Conference 2021
2020
ICPADS 2020CCF-C
A Learning-based Dynamic Load Balancing Approach for Microservice Systems in Multi-cloud Environment
In Proceedings of IEEE 26th International Conference on Parallel and Distributed Systems
ISSRE 2020CCF-B
SwissLog: Robust and Unified Deep Learning Based Log Anomaly Detection for Diverse Faults
In Proceedings of the 2020 IEEE 31st International Symposium on Software Reliability Engineering
IEEE Access 2020
A Framework of Virtual War Room and Matrix Sketch-Based Streaming Anomaly Detection for Microservice Systems
In IEEE Access
2019
ICWS 2019CCF-B
Microscaler: Automatic Scaling for Microservices with an Online Learning Approach
In Proceedings of the 2019 IEEE International Conference on Web Services