Publications ๐Ÿ“š

2026

Why Does the LLM Stop Computing: An Empirical Study of User-Reported Failures in Open-Source LLMs
Guangba Yu*, Zirui Wang*, Yujie Huang, Renyi Zhong, Yuedong Zhong, Yilun Wang, Haiyu Huang, Michael R. Lyuโ€ 
ISSTA'26 (CCF A) Under review at The 35th ACM SIGSOFT International Symposium on Software Testing and Analysis
AI-NativeBench: An Open-Source White-Box Agentic Benchmark Suite for AI-Native Systems
Zirui Wang*, Guangba Yu*โ€ , Michael R. Lyu
FSE'26 (CCF A) Accepted at The 34th ACM International Conference on the Foundations of Software Engineering Workshop on Data Intensive Software Engineering
TOSEM (CCF A) Extended version under review at The ACM Transactions on Software Engineering and Methodology
Cloud-OpsBench: A Reproducible Benchmark for Agentic Root Cause Analysis in Cloud Systems
Yilun Wang, Guangba Yuโ€ , Haiyu Huang, Yujie Huang, Zirui Wang, Pengfei Chen, Michael R. Lyu
ASE'26 (CCF A) Under review at The 41st IEEE/ACM International Conference on Automated Software Engineering
Memoir: Efficient KV Cache Optimization for LLM Inference in WebAssembly Runtimes
Zirui Wang, Yudan Long, Yuxin Suโ€ , Dan Li, Zibin Zheng
ICDCS'26 (CCF B) Under review at The 46th IEEE International Conference on Distributed Computing Systems