Agentic Memory Enhanced Recursive Reasoning for Root Cause Localization in Microservices
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915709771055104 |
|---|---|
| author | Zhang, Lingzhe Jia, Tong Zhai, Yunpeng Pan, Leyi Duan, Chiming He, Minghua Jia, Mengxi Li, Ying |
| author_facet | Zhang, Lingzhe Jia, Tong Zhai, Yunpeng Pan, Leyi Duan, Chiming He, Minghua Jia, Mengxi Li, Ying |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_02732 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Agentic Memory Enhanced Recursive Reasoning for Root Cause Localization in Microservices Zhang, Lingzhe Jia, Tong Zhai, Yunpeng Pan, Leyi Duan, Chiming He, Minghua Jia, Mengxi Li, Ying Software Engineering Artificial Intelligence 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. |
| title | Agentic Memory Enhanced Recursive Reasoning for Root Cause Localization in Microservices |
| topic | Software Engineering Artificial Intelligence |
| url | https://arxiv.org/abs/2601.02732 |