一句话：提出 OncallX，利用 LLM 多智能体协作实现工业场景事件自动响应、解决与分诊。
大规模企业中，on-call 工程师保障服务可用性，但事件数量与复杂度增长使传统人工流程日益不足。本文提出 OncallX，一个面向真实工业场景的端到端自动 on-call 系统，将 LLM 与多智能体协作结合用于事件管理。OncallX 先借助外部知识库与多轮对话增强用户查询，再由多个专家智能体通过树搜索机制协作生成响应与解决方案；无法自动解决时，系统将事件准确分派给最合适的团队。在全球顶级在线视频服务商的真实生产环境中，实验表明 OncallX 在自动指标与人工评估上均显著优于现有方法。系统已部署两个月，平均响应时间 21 秒、平均分诊时间 4 秒，显著提升 on-call 效率。
In large-scale enterprises, on-call engineers (OCEs) are critical for ensuring service availability and reliability. However, as incidents grow in volume and complexity, traditional manual on-call processes are becoming increasingly inadequate. Recent advances in large language models (LLMs) have demonstrated remarkable capabilities in reasoning and multi-agent collaboration, presenting new opportunities for automation. We propose OncallX, an end-to-end automated on-call system designed for real-world industrial scenarios that integrates LLMs with multi-agent cooperation to enable intelligent and efficient incident management. OncallX first enhances user queries by leveraging external knowledge bases and multi-turn dialogue interactions. Subsequently, multiple expert agents collaborate through tree-search-based mechanisms to generate effective responses and solutions. When incidents cannot be resolved automatically, OncallX accurately assigns them to the most appropriate teams. Comprehensive experiments conducted in the real-world production environment of a top-tier global online video service provider demonstrate that OncallX efficiently responds to incidents and accurately triages tickets, significantly outperforming existing methods in both automated metrics and human evaluations. Furthermore, OncallX has been successfully deployed in production for two months, during which it has substantially enhanced on-call efficiency, reducing average incident response time to just 21 seconds and average triage time to 4 seconds—representing a transformative improvement in operational excellence.
DOI 原文 ·
@inproceedings{paperbot9226,
title = {LLM-Powered Multi-Agent Collaboration for Intelligent Industrial On-Call Automation},
author = {Ruowei Fu and Yang Zhang and Zeyu Che and Xin Wu and Zhenyu Zhong and Zhiqiang Ren and Shenglin Zhang and Feng Wang and Yongqian Sun and Xiaozhou Liu and Kexin Liu and Yu Zhang},
booktitle = {ASE},
year = {2025},
doi = {10.1109/ase63991.2025.00184}
}