A graph-guided LLM agent framework for microservice root cause analysis reports AC@1 accuracy of about 74% on two benchmarks, outperforming the strongest LLM baseline by roughly 26 percentage points.
2025.Claude-sonnet-4-5 Release
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
method 1
citation-polarity summary
fields
cs.SE 1years
2026 1verdicts
CONDITIONAL 1roles
method 1polarities
use method 1representative citing papers
citing papers explorer
-
GALA: Graph-Augmented LLM Agents for Root Cause Analysis and Incident Response in Microservices
A graph-guided LLM agent framework for microservice root cause analysis reports AC@1 accuracy of about 74% on two benchmarks, outperforming the strongest LLM baseline by roughly 26 percentage points.