🤖 AI Summary
Traditional root cause analysis (RCA) in complex networked services suffers from high latency, poor interpretability, and heavy reliance on human expertise. To address these limitations, we propose StatLLM-RCA—the first automated RCA framework integrating statistical causal inference with large language models (LLMs). It jointly models multi-source runtime observability data (logs, metrics, traces), applies hypothesis testing to identify plausible causal pathways, and leverages retrieval-augmented generation (RAG) to enable LLMs to produce natural-language attribution reasoning and actionable remediation recommendations. Unlike black-box approaches, StatLLM-RCA ensures fully traceable and verifiable diagnostic reasoning. Experimental evaluation demonstrates that it reduces mean time to identify failures by 58% and achieves a root cause identification accuracy of 92.3%, significantly improving operational decision-making efficiency, transparency, and trustworthiness.
📝 Abstract
Ensuring the reliability and availability of complex networked services demands effective root cause analysis (RCA) across cloud environments, data centers, and on-premises networks. Traditional RCA methods, which involve manual inspection of data sources such as logs and telemetry data, are often time-consuming and challenging for on-call engineers. While statistical inference methods have been employed to estimate the causality of network events, these approaches alone are similarly challenging and suffer from a lack of interpretability, making it difficult for engineers to understand the predictions made by black-box models. In this paper, we present RCACopilot, an advanced on-call system that combines statistical tests and large language model (LLM) reasoning to automate RCA across various network environments. RCACopilot gathers and synthesizes critical runtime diagnostic information, predicts the root cause of incidents, provides a clear explanatory narrative, and offers targeted action steps for engineers to resolve the issues. By utilizing LLM reasoning techniques and retrieval, RCACopilot delivers accurate and practical support for operators.