RAG-Stack jointly optimizes RAG algorithm choices and serving-system settings via sub-metric-aware multi-objective Bayesian optimization plus an analytical performance model, reporting Pareto frontiers covering 52.5% to 153.2% more normalized quality-performance space than baselines.
Marker-Inc-Korea/AutoRAG
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.DB 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
RAG-Stack: Co-Optimizing RAG Serving Performance and Quality
RAG-Stack jointly optimizes RAG algorithm choices and serving-system settings via sub-metric-aware multi-objective Bayesian optimization plus an analytical performance model, reporting Pareto frontiers covering 52.5% to 153.2% more normalized quality-performance space than baselines.