A deployed RCA system using API-level drilldown, a skeleton causal graph, and memory-augmented multi-agent LLM reasoning localizes root-cause services and failure types with AC@1 of 0.88/0.79 in a 200k-service production environment.
arXiv preprint arXiv:2402.11068 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
Introduces EPC-AW to mitigate epistemic miscalibration in LLM multi-agent planning via consistency-based selection and refinement, reporting 9.75% average success improvement.
citing papers explorer
-
KRCA: An Efficient Root Cause Analysis System in Hyper-scale Microservice Systems via Agentic AI
A deployed RCA system using API-level drilldown, a skeleton causal graph, and memory-augmented multi-agent LLM reasoning localizes root-cause services and failure types with AC@1 of 0.88/0.79 in a 200k-service production environment.
-
When Planning Fails Despite Correct Execution: On Epistemic Calibration for LLM-Based Multi-Agent Systems
Introduces EPC-AW to mitigate epistemic miscalibration in LLM multi-agent planning via consistency-based selection and refinement, reporting 9.75% average success improvement.