GALA: Graph-Augmented LLM Agents for Root Cause Analysis and Incident Response in Microservices

2026-08-09

AI Summary

This work addresses the challenge of root cause analysis in microservices, which requires fusing heterogeneous telemetry data from multiple sources. While existing approaches are often limited to a single modality and generic large language models (LLMs) suffer from hallucination and lack actionable recommendations, we propose GALA+, a graph-augmented LLM agent framework. GALA+ leverages service dependency graphs to guide a graph-constrained reasoning mechanism that integrates multimodal telemetry—including logs, metrics, and traces—and incorporates the STRIX structure-aware scoring module to generate tiered response suggestions. We also introduce SURE-Score, an end-to-end evaluation framework incorporating expert feedback. Experiments show that GALA+ outperforms the best LLM baseline by over 25 percentage points in AC@1 on two microservice benchmarks and achieves state-of-the-art performance under both SURE-Score and SRE expert evaluations.

Abstract

Microservice root cause analysis (RCA) requires correlating failures across heterogeneous telemetry within complex service dependency graphs. Existing methods often rely on a single telemetry modality; recent LLM-based approaches can suffer from unconstrained exploration and hallucination; and most systems stop at fault ranking without producing actionable incident response. We present GALA+, a graph-augmented LLM agentic framework centered on graph-guided investigation, which uses service dependencies to bound exploration and refine diagnosis through localized multi-modal evidence. For initial hypothesis generation, GALA+ combines complementary telemetry signals with STRIX, a novel trace- and graph-structure-aware scoring module. GALA+ then produces ranked diagnoses, incident summaries, and stratified action recommendations. We further introduce SURE-Score, a human-guided evaluation framework co-developed with industry SRE experts for assessing RCA-specific output quality beyond conventional text similarity metrics. On two microservice benchmarks, GALA+ consistently achieves the strongest overall results, surpassing the best LLM-based baseline by more than 25 percentage points in AC@1, while also receiving the highest ratings from both SURE-Score and independent human SRE evaluation.

Problem

• root cause analysis
• microservices
• incident response
• telemetry correlation
• service dependency graph

Innovation

• graph-augmented LLM
• root cause analysis
• microservices
• multi-modal telemetry
• agentic framework