RCAgent: Cloud Root Cause Analysis by Autonomous Agents with Tool-Augmented Large Language Models

TL;DR

RCAgent is an autonomous, tool-augmented LLM framework designed for practical, privacy-aware cloud root cause analysis, outperforming existing methods in predicting causes, solutions, and responsibilities, with successful real-world integration.

Contribution

The paper introduces RCAgent, a novel autonomous agent framework that leverages tool augmentation and domain knowledge for improved cloud root cause analysis, surpassing prior approaches like ReAct.

Findings

RCAgent outperforms ReAct in root cause prediction accuracy.

RCAgent demonstrates consistent superiority across multiple RCA tasks.

Successfully integrated into Alibaba Cloud's real-time compute platform.

Abstract

Large language model (LLM) applications in cloud root cause analysis (RCA) have been actively explored recently. However, current methods are still reliant on manual workflow settings and do not unleash LLMs' decision-making and environment interaction capabilities. We present RCAgent, a tool-augmented LLM autonomous agent framework for practical and privacy-aware industrial RCA usage. Running on an internally deployed model rather than GPT families, RCAgent is capable of free-form data collection and comprehensive analysis with tools. Our framework combines a variety of enhancements, including a unique Self-Consistency for action trajectories, and a suite of methods for context management, stabilization, and importing domain knowledge. Our experiments show RCAgent's evident and consistent superiority over ReAct across all aspects of RCA -- predicting root causes, solutions, evidence, and responsibilities -- and tasks covered or uncovered by current rules, as validated by both automated metrics and human evaluations. Furthermore, RCAgent has already been integrated into the diagnosis and issue discovery workflow of the Real-time Compute Platform for Apache Flink of Alibaba Cloud.