ASE 2026 (series) / Industry Showcase /
OpsAgent: An Evolving Multi-agent System for Incident Management in Microservices
Tue 13 Oct 2026 11:30 - 11:45 at Forum 15 - Security and Other Non-Functional Properties: Reliability and Availability 1
Tue 13 OctDisplayed time zone: Amsterdam, Berlin, Bern, Rome, Stockholm, Vienna change
Tue 13 Oct
Displayed time zone: Amsterdam, Berlin, Bern, Rome, Stockholm, Vienna change
10:30 - 12:30 | Security and Other Non-Functional Properties: Reliability and Availability 1Research Papers / Industry Showcase at Forum 15 | ||
10:30 15mTalk | TELLER: Non-intrusive Cross-Layer Root-Cause Analysis for LLM Inference Research Papers Ruilin Xu Sun Yat-sen University, Junyi Li Sun Yat-sen University, Pengfei Chen Sun Yat-sen University, Zongxuan Xie Sun Yat-sen University | ||
10:45 15mTalk | When Does AI Actually Help in Incident Response? Identifying Good First Messages in Cloud Service Incidents Research Papers Minghua Ma Microsoft, Rujia Wang Microsoft, Chetan Bansal Microsoft Research, Saravan Rajmohan Microsoft, Yingnong Dang Microsoft Azure, Hongyu Zhang Chongqing University | ||
11:00 15mTalk | Expanding Guard Reach: Online Learning-Driven Incremental Kernel Panic Diagnosis Industry Showcase Yicheng Sui Nankai University, Xiaotian Wang Nankai University, Hailin Zhang Nankai University, Shenglin Zhang Nankai University, Binhong Jiang Nankai University, Heng Zheng Nankai University, Yongqian Sun Nankai University, Yuzhi Zhang Nankai University, Yang Zhang ByteDance Inc., Xin Wu ByteDance Inc., Liangyan Peng ByteDance, Linlin Han ByteDance, Feng Wang ByteDance Inc., Xiaozhou Liu ByteDance Inc., Yu Zhang ByteDance Inc. | ||
11:15 15mTalk | GALA: Graph-Augmented LLM Agents for Root Cause Analysis and Incident Response in Microservices Research Papers Yifang Tian University of Toronto, Yaming Liu University of Toronto, Zichun Chong University of Toronto, Zihang Huang University of Toronto, Yiran Li University of Toronto, Hans-Arno Jacobsen University of Toronto Pre-print | ||
11:30 15mTalk | OpsAgent: An Evolving Multi-agent System for Incident Management in Microservices Industry Showcase Yu Luo Nankai University, Jiamin Jiang Nankai University, Jingfei Feng Nankai University, Lei Tao Nankai University, Qingliang Zhang Nankai University, Xidao Wen Alibaba Cloud, Yongqian Sun Nankai University, Shenglin Zhang Nankai University, Tong Liu Lenovo (TianJin) Co., Ltd., Wenjie Zhang Lenovo, Dan Pei Tsinghua University, China | ||
11:45 15mTalk | ActionNex: A Production-Grade System for Next-Best-Action Recommendation in Cloud Outage Management Industry Showcase Zhenfeng Lin Microsoft, Haoji Hu Microsoft, Ming Hao Microsoft, Xuchao Zhang Microsoft, Yudi He Microsoft, Oleg Kulygin Microsoft, Hatay Tuna Microsoft, Chetan Bansal Microsoft Research, Ze Li Microsoft Azure, Murali Chintalapati Microsoft Azure, Sheila Jiang Microsoft, Salman Zafar Microsoft, Angie Anderson Microsoft, Ryan zhang | ||
12:00 15mTalk | ReLog: Execution-Aware Logging with Runtime Feedback for LLM-Oriented Debugging Research Papers Xin Wang The Hong Kong University of Science and Technology (Guangzhou), Yang Feng The Hong Kong University of Science and Technology (Guangzhou), Xiaoqian Jiao Hong Kong University of Science and Technology, Yang Zhang Hebei University of Science and Technology, Zhenhao Li York University, Zishuo Ding The Hong Kong University of Science and Technology (Guangzhou) Pre-print | ||
12:15 15mTalk | Towards Reliable Alarm Flood Reduction in Data Center via Grammar-Guided Verifiable LLM Reasoning Industry Showcase Jiacheng Liu Peking University; Institute for AI Industry Research (AIR), Tsinghua University, Guocong Lin Tsinghua University, Jichao Yan Tsinghua University, Huiwen Zheng GDS Holdings, Hongli Ma GDS Holdings, Changhao Zhou GDS Holdings, Zhiyi Yu GDS Holdings, Yuanchun Li Institute for AI Industry Research (AIR), Tsinghua University, Yunxin Liu Tsinghua University, Ding Li Peking University, Tao Xie Peking University, Yao Guo Peking University | ||