AutoRAGTuner: A Declarative Framework for Automatic Optimization of RAG Pipelines

TL;DR

AutoRAGTuner is a flexible, declarative framework that automates the construction, tuning, and evaluation of RAG pipelines, significantly reducing manual effort and improving performance across diverse architectures.

Contribution

It introduces a modular, declarative system with a novel Domain-Element Model and Bayesian optimization for end-to-end hyper-parameter tuning of RAG pipelines.

Findings

AutoRAGTuner outperforms default baselines across various RAG architectures.

The framework reduces code churn by up to 95% during architectural adjustments.

It demonstrates architectural generality and efficiency in hyper-parameter optimization.

Abstract

Retrieval-Augmented Generation (RAG) enhances LLMs, but performance is highly sensitive to complex architecture designs and hyper-parameter configurations, which currently rely on inefficient manual tuning. We present AutoRAGTuner, a declarative, configuration-driven framework that automates the RAG life cycle: construction, execution,evaluation, and optimization. AutoRAGTuner employs a modular architecture to decouple pipeline stages through a component registration mechanism. To unify heterogeneous data, we introduce the Domain-Element Model (DEM), representing objects as atomic elements with bidirectional pointers to support nodes, edges, and hyperedges. Furthermore, AutoRAGTuner integrates an adaptive Bayesian optimization engine for end-to-end hyper-parameter tuning. Experimental results demonstrate AutoRAGTuner's architectural generality: across diverse RAG pipelines, ranging from vanilla to graph-based, the framework consistently outperforms default baselines. Notably, AutoRAGTuner significantly mitigates engineering overhead, where its declarative configuration language enables a up to 95\% reduction in code churn for architectural adjustments. Overall, AutoRAGTuner provides a systematically optimizable foundation for building evolvable and reusable RAG systems.