LLexus: an AI agent system for incident management-Reference-Cited by-同舟云学术

LLexus: an AI agent system for incident management

Published:2024-08-14 Issue:1 Volume:58 Page:23-36
ISSN:0163-5980
Container-title:ACM SIGOPS Operating Systems Review
language:en
Short-container-title:SIGOPS Oper. Syst. Rev.

Author:

Las-Casas Pedro¹,Kumbhare Alok Gautum¹,Fonseca Rodrigo¹,Agarwal Sharad¹

Affiliation:

1. Microsoft

Abstract

When operating a software service on a cloud, the complexity of keeping multiple distributed components responsive is a significant challenge for engineering teams. Engineers frequently rely on Troubleshooting Guides (TSGs) to navigate how to mitigate performance or outage incidents. However, the effectiveness of TSGs is often hindered by their length, implicit reliance on tribal knowledge, and the variable quality of their content. This paper introduces LLexus, an agent-based AI system to automate the execution of TSGs.

Publisher

Association for Computing Machinery (ACM)

Link

https://dl.acm.org/doi/pdf/10.1145/3689051.3689056

Reference35 articles.

1. Toufique Ahmed, Supriyo Ghosh, Chetan Bansal, Thomas Zimmermann, Xuchao Zhang, and Saravan Rajmohan. Recommending rootcause and mitigation steps for cloud incidents using large language models. In 2023 IEEE/ACM 45th International Conference on Software Engineering (ICSE), pages 1737--1749. IEEE, 2023.

2. Kaikai An, Fangkai Yang, Liqun Li, Zhixing Ren, Hao Huang, LuWang, Pu Zhao, Yu Kang, Hua Ding, Qingwei Lin, Saravan Rajmohan, and Qi Zhang. Nissist: An incident mitigation copilot based on troubleshooting guides. arXiv preprint arXiv:2402.17531, 2024.

3. DeCaf

4. Sébastien Bubeck, Varun Chandrasekaran, Ronen Eldan, Johannes Gehrke, Eric Horvitz, Ece Kamar, Peter Lee, Yin Tat Lee, Yuanzhi Li, Scott Lundberg, Harsha Nori, Hamid Palangi, Marco Tulio Ribeiro, and Yi Zhang. Sparks of artificial general intelligence: Early experiments with gpt-4. arXiv preprint arXiv:2303.12712, 2023.

5. An Empirical Investigation of Incident Triage for Online Service Systems