一句话：提出多智能体事件分诊系统 Triangle，以语义蒸馏和协商机制提升云服务分诊准确率并降低参与时间。
随着云服务规模与复杂度增长，意外中断与故障不可避免，快速准确地将事件分派给责任团队对保障可靠性和减少损失至关重要。现有依赖人工和预定义规则的方法难以应对异构事件数据与多团队动态知识。为此，作者提出端到端多智能体事件分诊系统 Triangle：用语义蒸馏缓解事件数据语义异构，引入多角色智能体与协商机制模拟工程师工作流以处理去中心化动态知识，并自动收集排障信息与缓解；在真实云生产环境实验中，分诊准确率最高达 97%，参与时间（TTE）最多降低 91%，显著提升多种云服务的运营效率。
As cloud service systems grow in scale and complexity, incidents that indicate unplanned interruptions and outages become unavoidable. Rapid and accurate triage of these incidents to the appropriate responsible teams is crucial to maintain service reliability and prevent significant financial losses. However, existing incident triage methods relying on manual operations and predefined rules often struggle with efficiency and accuracy due to the heterogeneity of incident data and the dynamic nature of domain knowledge across multiple teams.To solve these issues, we propose Triangle, an end-to-end incident triage system based on a Multi-Agent framework. Triangle leverages a semantic distillation mechanism to tackle the issue of semantic heterogeneity in incident data, enhancing the accuracy of incident triage. Additionally, we introduce multi-role agents and a negotiation mechanism to emulate human engineers’ workflows, effectively handling decentralized and dynamic domain knowledge from multiple teams. Furthermore, our system incorporates an automated troubleshooting information collection and mitigation mechanism, reducing the reliance on human labor and enabling fully automated end-to-end incident triage. Extensive experiments conducted on a real-world cloud production environment demonstrate that Triangle significantly improved incident triage accuracy (up to 97%) and reduced Time to Engage (TTE) by as much as 91%, demonstrating substantial operational impact across diverse cloud services.
DOI 原文 ·
@inproceedings{paperbot9560,
title = {Triangle: Empowering Incident Triage with Multi-Agent},
author = {Zhaoyang Yu and Aoyang Fang and Minghua Ma and Jaskaran Singh Walia and Chaoyun Zhang and Shu Chi and Ze Li and Murali Chintalapati and Xuchao Zhang and Rujia Wang and Chetan Bansal and Saravan Rajmohan and Qingwei Lin and Shenglin Zhang and Dan Pei and Pinjia He},
booktitle = {ASE},
year = {2025},
doi = {10.1109/ase63991.2025.00062}
}