Towards In-Depth Root Cause Localization for Microservices with Multi-Agent Recursion-of-Thought

• URL: http://arxiv.org/abs/2605.14866v1
• Date: Thu, 14 May 2026 14:13:59 GMT
• Title: Towards In-Depth Root Cause Localization for Microservices with Multi-Agent Recursion-of-Thought
• Abstract summary: We introduce RCLAgent, an in-depth root cause localization framework for microservice systems.<n>RCLAgent decomposes the diagnostic process along the trace graph by assigning each span to a Dedicated Agent.<n>It consistently outperforms state-of-the-art methods in both localization accuracy and inference efficiency.
• Score: 22.98209081540165
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: As modern microservice systems grow increasingly complex due to dynamic interactions and evolving runtime environments, they experience failures with rising frequency. Ensuring system reliability therefore critically depends on accurate root cause localization (RCL). While numerous traditional machine learning and deep learning approaches have been explored for this task, they often suffer from limited interpretability and poor transferability across deployments. More recently, large language model (LLM)-based methods have been proposed to address these issues. However, existing LLM-based approaches still face two fundamental limitations: context explosion, which dilutes critical evidence and degrades localization accuracy, and serial reasoning structures, which hinder deep causal exploration and impair inference efficiency. In this paper, we conduct a comprehensive study of both how human SREs perform root cause localization in practice and why existing LLM-based methods fall short. Motivated by these findings, we introduce RCLAgent, an in-depth root cause localization framework for microservice systems that realizes multi-agent recursion-of-thought with parallel reasoning. RCLAgent decomposes the diagnostic process along the trace graph by assigning each span to a Dedicated Agent and organizing agents recursively and in parallel according to the graph topology, with the final diagnosis obtained by synthesizing the Root-Level Diagnosis Report and the Global Evidence Graph. Extensive experiments on multiple public benchmarks demonstrate that RCLAgent consistently outperforms state-of-the-art methods in both localization accuracy and inference efficiency.

Related papers

• Causal Ensemble Agent: Hierarchical Causal Discovery with LLM-guided Expert Reweighting [95.24017293537025]
  Causal Ensemble Agent (CEA) is a novel framework that aggregates structural insights from statistical discovery experts across different graph levels.<n>CEA achieves the strongest overall performance across a wide range of causal discovery methods.
  arXiv  Detail & Related papers  (2026-06-09T09:09:07Z)
• METER: Evaluating Multi-Level Contextual Causal Reasoning in Large Language Models [61.33372454250959]
  Contextual causal reasoning is a critical yet challenging capability for Large Language Models.<n>Existing benchmarks fail to ensure context consistency or cover the full causal hierarchy.<n>We pioneer METER to systematically benchmark LLMs across all three levels of the causal ladder.
  arXiv  Detail & Related papers  (2026-04-13T14:07:11Z)
• Search-R2: Enhancing Search-Integrated Reasoning via Actor-Refiner Collaboration [49.9937230730202]
  We propose Search-R2, a novel Actor-Refiner collaboration framework that enhances reasoning through targeted intervention.<n>Our approach decomposes the generation process into an Actor, which produces initial reasoning trajectories.<n>We show that Search-R2 consistently outperforms strong RAG and RL-based baselines across model scales.
  arXiv  Detail & Related papers  (2026-02-03T15:32:09Z)
• Hypothesize-Then-Verify: Speculative Root Cause Analysis for Microservices with Pathwise Parallelism [19.31110304702373]
  SpecRCA is a speculative root cause analysis framework that adopts a textithypothesize-then-verify paradigm.<n>Preliminary experiments on the AIOps 2022 demonstrate that SpecRCA achieves superior accuracy and efficiency compared to existing approaches.
  arXiv  Detail & Related papers  (2026-01-06T05:58:25Z)
• Agentic Memory Enhanced Recursive Reasoning for Root Cause Localization in Microservices [19.187189391947815]
  Site Reliability Engineers (SREs) localize the root causes of failures.<n>Traditional graph-based and deep learning approaches often rely heavily on pre-defined schemas.<n>We introduce AMER-RCL, an agentic memory enhanced framework for root cause localization.
  arXiv  Detail & Related papers  (2026-01-06T05:50:14Z)
• SelfAI: Building a Self-Training AI System with LLM Agents [79.10991818561907]
  SelfAI is a general multi-agent platform that combines a User Agent for translating high-level research objectives into standardized experimental configurations.<n>An Experiment Manager orchestrates parallel, fault-tolerant training across heterogeneous hardware while maintaining a structured knowledge base for continuous feedback.<n>Across regression, computer vision, scientific computing, medical imaging, and drug discovery benchmarks, SelfAI consistently achieves strong performance and reduces redundant trials.
  arXiv  Detail & Related papers  (2025-11-29T09:18:39Z)
• Root Cause Analysis for Microservice Systems via Cascaded Conditional Learning with Hypergraphs [6.06702225930801]
  Root cause analysis in microservice systems typically involves two core tasks: root cause localization (RCL) and failure type identification (FTI)<n>These methods predominantly adopt a joint learning paradigm for RCL and FTI to exploit shared information and reduce training time.<n>We propose CCLH, a novel root cause analysis framework that orchestrates diagnostic tasks based on cascaded conditional learning.
  arXiv  Detail & Related papers  (2025-11-14T03:20:02Z)
• Adaptive Root Cause Localization for Microservice Systems with Multi-Agent Recursion-of-Thought [11.307072056343662]
  We introduce RCLAgent, an adaptive root cause localization method for microservice systems.<n>We show that RCLAgent achieves superior performance by localizing the root cause using only a single request-outperforming state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-08-28T02:34:19Z)
• Online Multi-modal Root Cause Analysis [61.94987309148539]
  Root Cause Analysis (RCA) is essential for pinpointing the root causes of failures in microservice systems. Existing online RCA methods handle only single-modal data overlooking, complex interactions in multi-modal systems. We introduce OCEAN, a novel online multi-modal causal structure learning method for root cause localization.
  arXiv  Detail & Related papers  (2024-10-13T21:47:36Z)
• 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)

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.