KRCA: An Efficient Root Cause Analysis System in Hyper-Scale Microservice Systems via Agentic AI

• URL: http://arxiv.org/abs/2607.01788v1
• Date: Thu, 02 Jul 2026 07:01:12 GMT
• Title: KRCA: An Efficient Root Cause Analysis System in Hyper-Scale Microservice Systems via Agentic AI
• Abstract summary: Hyper-scale microservice systems have become the standard infrastructure for large-scale Internet companies.<n>Existing Root Cause Analysis (RCA) methods often struggle to adapt to the extreme dynamism and massive scale of these systems.<n>We present KRCA, an end-to-end RCA system designed for hyper-scale microservice systems.
• Score: 14.531960390639343
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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 employs 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 lease 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%.

Related papers

• Root Cause Analysis with Latent Confounders using Partial Ancestral Graphs [0.8602553195689513]
  Finding the source of failures is essential for identifying the root causes of anomalies and maintaining the reliability of complex systems.<n>While causal theory has advanced data-driven Root Cause Analysis, existing frameworks assume causal sufficiency, failing to account for the unobserved latent variables prevalent in real-world environments.<n>This framework models system failures as parametric interventions over Partial Ancestral Graphs (PAGs) to perform RCA in the presence of latent variables.
  arXiv  Detail & Related papers  (2026-06-18T20:08:34Z)
• Anomaly Detection and Root Cause Analysis for Microservice Systems [0.0]
  Microservice systems are widely used to build cloud applications, yet their complexity makes failures inevitable.<n>This thesis advances automated anomaly detection and root cause analysis for microservice failures.
  arXiv  Detail & Related papers  (2026-06-08T00:50:43Z)
• Towards a Virtual Neuroscientist: Autonomous Neuroimaging Analysis via Multi-Agent Collaboration [53.772014300855375]
  We introduce NIAgent, a multi-agent system for autonomous end-to-end neuroimaging analysis.<n>Unlike conventional flat tool-calling agents, NIAgent adopts a code-centric execution paradigm.<n>We propose a hierarchical verification framework for autonomous quality control, integrating cohort-level metric screening with agentic visual inspection.
  arXiv  Detail & Related papers  (2026-05-10T06:30:19Z)
• Multi-Agent Systems for Root Cause Analysis in Microservices [58.95503998127531]
  LATS-RCA is a multi-agent framework for root cause analysis in MSS.<n> Reflection scores are used to guide the search toward the most likely root cause.<n>We evaluate LATS-RCA on the open-source industrial MSS, Light-OAuth2.
  arXiv  Detail & Related papers  (2026-05-05T08:39:42Z)
• MetaRCA: A Generalizable Root Cause Analysis Framework for Cloud-Native Systems Powered by Meta Causal Knowledge [3.8594782754324535]
  The dynamics and complexity of cloud-native systems present significant challenges for Root Cause Analysis (RCA)<n>This paper introduces MetaRCA, a generalizable RCA framework for cloud-native systems.
  arXiv  Detail & Related papers  (2026-03-02T16:16:22Z)
• Cloud-OpsBench: A Reproducible Benchmark for Agentic Root Cause Analysis in Cloud Systems [51.2882705779387]
  Cloud-OpsBench is a large-scale benchmark that employs a State Snapshot Paradigm to construct a deterministic digital twin of the cloud.<n>It features 452 distinct fault cases across 40 root cause types spanning the full stack.
  arXiv  Detail & Related papers  (2026-02-28T05:04:42Z)
• Graph-Free Root Cause Analysis [0.0]
  We propose PRISM, a simple and efficient framework for Root Cause Analysis.<n>On 735 failures across 9 real-world datasets, PRISM achieves 68% Top-1 accuracy, a 258% improvement over the best baseline, while requiring only 8ms per diagnosis.
  arXiv  Detail & Related papers  (2026-01-29T07:38:20Z)
• LLM-Augmented Knowledge Base Construction For Root Cause Analysis [0.6439596199812365]
  This study evaluates three Large Language Model (LLM) methodologies for constructing a Root Cause Analysis (RCA) Knowledge Base from support tickets.<n>We compare their performance using a comprehensive suite of lexical and semantic similarity metrics.<n>Our experiments on a real industrial dataset demonstrate that the generated knowledge base provides an excellent starting point for accelerating RCA tasks.
  arXiv  Detail & Related papers  (2026-01-09T16:41:30Z)
• Multi-modal Causal Structure Learning and Root Cause Analysis [67.67578590390907]
  We propose Mulan, a unified multi-modal causal structure learning method for root cause localization. We leverage a log-tailored language model to facilitate log representation learning, converting log sequences into time-series data. We also introduce a novel key performance indicator-aware attention mechanism for assessing modality reliability and co-learning a final causal graph.
  arXiv  Detail & Related papers  (2024-02-04T05:50:38Z)
• TraceDiag: Adaptive, Interpretable, and Efficient Root Cause Analysis on Large-Scale Microservice Systems [44.53009495726297]
  Root Cause Analysis (RCA) is becoming increasingly crucial for ensuring the reliability of microservice systems. This paper proposes TraceDiag, an end-to-end RCA framework that addresses the challenges for large-scale microservice systems.
  arXiv  Detail & Related papers  (2023-10-28T15:49:00Z)
• Disentangled Causal Graph Learning for Online Unsupervised Root Cause Analysis [49.910053255238566]
  Root cause analysis (RCA) can identify the root causes of system faults/failures by analyzing system monitoring data. Previous research has mostly focused on developing offline RCA algorithms, which often require manually initiating the RCA process. We propose CORAL, a novel online RCA framework that can automatically trigger the RCA process and incrementally update the RCA model.
  arXiv  Detail & Related papers  (2023-05-18T01:27:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.