AI Paper Atlas

Research map / Multi-agent systems and games / LLM agents

RCAFlow: A Workflow-Informed Hierarchical Planning Multi-Agent System for Root Cause Analysis

Yufei Gao, Zhengong Cai, Bowei Yang

AAAI 2026 · Multi-agent systems and games › LLM agents · approach: Agent data synthesis and behavior studies · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes RCAFlow, a workflow-informed hierarchical planning multi-agent LLM system for root cause analysis of microservice failures.

Problem

Root cause analysis in complex microservice systems, where existing deep learning methods lack flexibility and interpretability and prior LLM-based approaches are limited.

Approach

A multi-agent system that combines workflow information with hierarchical planning to structure LLM-driven root cause analysis, as described by the title and the partial abstract; further details are not available from the abstract alone.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add workflow knowledge base (ablation)RCAFlow (DeepSeek-V3) · OpenRCA BankCorrect accuracy (%): 12.50 -> 40.44Improved
add workflow knowledge base (ablation)RCAFlow (DeepSeek-V3) · OpenRCA TelecomCorrect accuracy (%): 15.69 -> 47.06Improved
add Git-inspired branch coordinator (ablation)RCAFlow (DeepSeek-V3) · OpenRCA BankCorrect accuracy (%): 25.00 -> 40.44Improved
add Planner with semantic retrieval (ablation)RCAFlow (DeepSeek-V3) · OpenRCA BankCorrect accuracy (%): 29.41 -> 40.44Improved
add state-aware analyzer (ablation)RCAFlow (DeepSeek-V3) · OpenRCA BankCorrect accuracy (%): 34.56 -> 40.44Improved
add reflection module (ablation)RCAFlow (DeepSeek-V3) · OpenRCA BankCorrect accuracy (%): 33.82 -> 40.44Improved
add few extra SOPs to the workflowRCAFlow (DeepSeek-V3) · OpenRCA BankCorrect accuracy (%): 40.44 -> 43.38Improved
raise confidence threshold theta (ablation)RCAFlow (DeepSeek-V3) · OpenRCA BankCorrect accuracy (%): rise-then-fall; APL increasesMixed
use RCAFlow instead of Flow-of-ActionGPT-4o · OpenRCA BankCorrect accuracy (%): 27.94 -> 41.91Improved
use RCAFlow instead of mABCRCAFlow (DeepSeek-V3) · OpenRCA MarketCorrect accuracy (%): 20.95 -> 34.46Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy