Hypothesize-Then-Verify: Speculative Root Cause Analysis for Microservices with Pathwise Parallelism

TL;DR

This paper introduces SpecRCA, a novel root cause analysis framework for microservices that uses a hypothesize-then-verify approach to improve accuracy and efficiency in identifying anomalies.

Contribution

The paper presents a new speculative RCA framework that enhances exploration diversity and reduces inference time compared to existing LLM-based methods.

Findings

Achieves higher accuracy than existing methods on AIOps 2022 dataset.

Demonstrates improved efficiency in root cause verification.

Shows potential for scalable and interpretable RCA in microservices.

Abstract

Microservice systems have become the backbone of cloud-native enterprise applications due to their resource elasticity, loosely coupled architecture, and lightweight deployment. Yet, the intrinsic complexity and dynamic runtime interactions of such systems inevitably give rise to anomalies. Ensuring system reliability therefore hinges on effective root cause analysis (RCA), which entails not only localizing the source of anomalies but also characterizing the underlying failures in a timely and interpretable manner. Recent advances in intelligent RCA techniques, particularly those powered by large language models (LLMs), have demonstrated promising capabilities, as LLMs reduce reliance on handcrafted features while offering cross-platform adaptability, task generalization, and flexibility. However, existing LLM-based methods still suffer from two critical limitations: (a) limited exploration diversity, which undermines accuracy, and (b) heavy dependence on large-scale LLMs, which results in slow inference. To overcome these challenges, we propose SpecRCA, a speculative root cause analysis framework for microservices that adopts a \textit{hypothesize-then-verify} paradigm. SpecRCA first leverages a hypothesis drafting module to rapidly generate candidate root causes, and then employs a parallel root cause verifier to efficiently validate them. Preliminary experiments on the AIOps 2022 dataset demonstrate that SpecRCA achieves superior accuracy and efficiency compared to existing approaches, highlighting its potential as a practical solution for scalable and interpretable RCA in complex microservice environments.