Diagnosing and Resolving Cloud Platform Instability with Multi-modal RAG LLMs

TL;DR

This paper introduces ARCA, a multi-modal RAG LLM system designed to diagnose and resolve cloud platform instability more effectively by leveraging AI pattern matching and natural language interfaces, outperforming existing solutions.

Contribution

The paper presents ARCA, a novel multi-modal RAG LLM system tailored for cloud stability diagnosis, demonstrating superior performance over current methods.

Findings

ARCA outperforms state-of-the-art alternatives in evaluations.

Multi-modal RAG LLMs enhance problem identification in cloud systems.

ARCA simplifies root cause analysis for complex cloud issues.

Abstract

Today's cloud-hosted applications and services are complex systems, and a performance or functional instability can have dozens or hundreds of potential root causes. Our hypothesis is that by combining the pattern matching capabilities of modern AI tools with a natural multi-modal RAG LLM interface, problem identification and resolution can be simplified. ARCA is a new multi-modal RAG LLM system that targets this domain. Step-wise evaluations show that ARCA outperforms state-of-the-art alternatives.