Integrating Large Language Models with Cloud-Native Observability for Automated Root Cause Analysis and Remediation

Abstract

Cloud-native systems based on microservices, containers, and serverless architectures present unprecedented challenges for observability and incident management. Traditional rule-based monitoring and manual root cause analysis are increasingly inadequate for handling the complexity and scale of modern distributed systems. This paper presents a novel framework that leverages large language models (LLMs) to enhance cloud-native observability, enabling automated root cause analysis and self-healing capabilities. Our system integrates OpenTelemetry-based telemetry collection with a domain-adapted LLM capable of performing multimodal analysis over metrics, logs, and traces. Through fine-tuning on operational data and chain-of-thought reasoning, the LLM generates explainable root cause hypotheses and actionable remediation plans. Experimental evaluation on public microservice datasets demonstrates that our approach reduces mean time to resolution (MTTR) by 84.2% compared to rule-based methods, achieving 95% F1-score in anomaly detection while maintaining low computational overhead. The system successfully automated 91% of common incidents without human intervention, significantly improving service reliability and reducing operational burden.