AutoRAGTuner: A Declarative Framework for Automatic Optimization of RAG Pipelines

2026-05-03

AI Summary

Current RAG systems heavily rely on manual tuning, resulting in substantial engineering overhead and low efficiency. This work proposes a declarative, configuration-driven automation framework that decouples the entire pipeline—construction, execution, evaluation, and optimization—through a modular architecture. The framework introduces a unified Domain-Element data model and an adaptive Bayesian optimization engine to enable end-to-end automatic tuning. It features a novel declarative configuration language that drastically reduces code modifications by up to 95%. Evaluated across diverse RAG architectures, the framework consistently outperforms default baselines, demonstrating both generality and high efficiency.

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.

Problem

• Retrieval-Augmented Generation
• hyper-parameter tuning
• pipeline optimization
• manual tuning
• RAG architecture

Innovation

• AutoRAGTuner
• Declarative Framework
• Domain-Element Model
• Bayesian Optimization
• RAG Pipeline Optimization