一句话：提出 KRCA，用 API 下钻、骨架因果图和记忆增强多智能体实现超大规模微服务根因定位与故障分类。
超大规模微服务系统由大量松耦合、持续独立演化的服务构成，故障难以避免，而现有根因分析（RCA）方法难以适应其极端动态性和巨大规模。本文提出端到端 RCA 系统 KRCA：首先通过 API 级下钻隔离可疑服务，然后从异常指标构建基于骨架的因果图作为高召回结构先验，最后利用记忆增强的多智能体框架验证因果关系并生成故障报告。该方法将结构化因果约束与多智能体推理结合，在诊断准确性与实时生产效率之间取得平衡。实验表明，KRCA 在根因服务定位和故障类型分类上的 AC@1 分别达到 0.88 和 0.79，较最强基线至少绝对提升 31%；系统已在快手生产环境部署超过六个月，平均诊断时间降低 77.3%。
Hyper-scale microservice systems have become the standard infrastructure for large-scale Internet companies. These systems consist of numerous loosely coupled microservices that evolve independently through continuous development and deployment. Such complexity makes failures unavoidable, necessitating efficient Root Cause Analysis (RCA) to help Site Reliability Engineers (SREs) quickly localize root cause services and classify failure types. However, existing RCA methods often struggle to adapt to the extreme dynamism and massive scale of these systems. In this paper, we present KRCA, an end-to-end RCA system designed for hyper-scale microservice systems. To manage the vast search space, KRCA employs a multi-stage pipeline that begins with an API-level drilldown to isolate suspicious services. It then instantiates a skeleton-based causal graph from anomalous metrics to serve as a high-recall structural prior, before utilizing a memory-augmented multi-agent framework to verify causality and generate the final failure report. By combining structured causal constraints with multi-agent reasoning, KRCA balances diagnostic accuracy with the efficiency requirements of real-time production use. Experimental results show that KRCA achieves AC@1 scores of 0.88 and 0.79 for root cause service localization and failure type classification, outperforming the strongest baseline by at least 31% in absolute gains. KRCA has been deployed in Kuaishou's production environment for over six months, reducing the average diagnosis time by 77.3%.
@inproceedings{abs-2607-01788,
title = {KRCA: An Efficient Root Cause Analysis System in Hyper-scale Microservice Systems via Agentic AI},
author = {Jiamin Jiang and Jingfei Feng and Yu Luo and Qingliang Zhang and Yongqian Sun and Wenwei Gu and Shenglin Zhang and Tianyu Cui and Yao Wu and Jielong Huang and Nan Qi and Dan Pei},
booktitle = {ASE},
year = {2026},
doi = {10.1145/3832783.3834468}
}