Agentic Memory Enhanced Recursive Reasoning for Root Cause Localization in Microservices
Open Access
- 12 April 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 58-69
Abstract
As contemporary microservice systems become increasingly popular and complex—often comprising hundreds or even thousands of fine-grained, interdependent subsystems—they are experiencing more frequent failures. Ensuring system reliability thus demands accurate root cause localization. While many traditional graph-based and deep learning approaches have been explored for this task, they often rely heavily on pre-defined schemas that struggle to adapt to evolving operational contexts. Consequently, a number of LLM-based methods have recently been proposed. However, these methods still face two major limitations: shallow, symptom-centric reasoning that undermines accuracy, and a lack of cross-alert reuse that leads to redundant reasoning and high latency. In this paper, we conduct a comprehensive study of how Site Reliability Engineers (SREs) localize the root causes of failures, drawing insights from professionals across multiple organizations. Our investigation reveals that expert root cause analysis exhibits three key characteristics: recursiveness, multi-dimensional expansion, and cross-modal reasoning. Motivated by these findings, we introduce AMER-RCL, an agentic memory enhanced recursive reasoning framework for root cause localization in microservices. AMER-RCL employs the Recursive Reasoning RCL engine, a multi-agent framework that performs recursive reasoning on each alert to progressively refine candidate causes, while Agentic Memory incrementally accumulates and reuses reasoning from prior alerts within a time window to reduce redundant exploration and lower inference latency. Experimental results demonstrate that AMER-RCL consistently outperforms state-of-the-art methods in both localization accuracy and inference efficiency.Keywords
All Related Versions
Funding Information
- Key RD Project of Guangdong Province (2020B010164003)
This publication has 56 references indexed in Scilit:
- LogAction: Consistent Cross-system Anomaly Detection through Logs via Active Domain Adaptation2025
- ScalaLog: Scalable Log-Based Failure Diagnosis Using LLM2025
- AnomalyLLM: Few-Shot Anomaly Edge Detection for Dynamic Graphs Using Large Language Models2024
- KGroot: A knowledge graph-enhanced method for root cause analysisExpert Systems with Applications, 2024
- A survey on intelligent management of alerts and incidents in IT servicesJournal of Network and Computer Applications, 2024
- Time-tired compaction: An elastic compaction scheme for LSM-tree based time-series databaseAdvanced Engineering Informatics, 2023
- Separation or Not: On Handing Out-of-Order Time-Series Data in Leveled LSM-Tree2022
- Design, monitoring, and testing of microservices systems: The practitioners’ perspectiveJournal of Systems and Software, 2021
- Trace-based Intelligent Fault Diagnosis for Microservices with Deep Learning2021
- Microscope: Pinpoint Performance Issues with Causal Graphs in Micro-service Environments2018