RAGSmith: A Framework for Finding the Optimal Composition of Retrieval-Augmented Generation Methods Across Datasets

📅 2025-11-03
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
Traditional RAG systems suffer from suboptimal performance due to tight coupling among retrieval, reranking, prompt rewriting, and generation modules, hindering holistic optimization. Method: This paper proposes the first end-to-end RAG architecture search framework, modeling the RAG configuration space as an evolvable search problem and employing genetic algorithms to jointly optimize multi-objective metrics—including recall@k/nDCG for retrieval and LLM-Judge/semantic similarity for generation. The framework encompasses nine component types across vector retrieval, reranking, and prompt rewriting. Contribution/Results: Evaluated across six domains, the framework achieves an average 3.8% performance gain (up to +12.5% in retrieval, +7.5% in generation) while converging after exploring only 0.2% of the configuration space. It identifies robust architectural patterns transferable across datasets and quantifies how domain characteristics and question types systematically influence optimal configurations.

Technology Category

Application Category

📝 Abstract
Retrieval-Augmented Generation (RAG) quality depends on many interacting choices across retrieval, ranking, augmentation, prompting, and generation, so optimizing modules in isolation is brittle. We introduce RAGSmith, a modular framework that treats RAG design as an end-to-end architecture search over nine technique families and 46{,}080 feasible pipeline configurations. A genetic search optimizes a scalar objective that jointly aggregates retrieval metrics (recall@k, mAP, nDCG, MRR) and generation metrics (LLM-Judge and semantic similarity). We evaluate on six Wikipedia-derived domains (Mathematics, Law, Finance, Medicine, Defense Industry, Computer Science), each with 100 questions spanning factual, interpretation, and long-answer types. RAGSmith finds configurations that consistently outperform naive RAG baseline by +3.8% on average (range +1.2% to +6.9% across domains), with gains up to +12.5% in retrieval and +7.5% in generation. The search typically explores $approx 0.2%$ of the space ($sim 100$ candidates) and discovers a robust backbone -- vector retrieval plus post-generation reflection/revision -- augmented by domain-dependent choices in expansion, reranking, augmentation, and prompt reordering; passage compression is never selected. Improvement magnitude correlates with question type, with larger gains on factual/long-answer mixes than interpretation-heavy sets. These results provide practical, domain-aware guidance for assembling effective RAG systems and demonstrate the utility of evolutionary search for full-pipeline optimization.
Problem

Research questions and friction points this paper is trying to address.

Optimizing modular RAG pipeline configurations across datasets
Finding optimal combinations of retrieval and generation techniques
Improving RAG performance through evolutionary architecture search
Innovation

Methods, ideas, or system contributions that make the work stand out.

Genetic search optimizes retrieval and generation metrics jointly
Framework explores 46080 configurations across nine technique families
Discovers robust backbone with domain-dependent augmentation choices
🔎 Similar Papers
No similar papers found.
M
Muhammed Yusuf Kartal
TOBB University of Economics and Technology
S
Suha Kagan Kose
Roketsan Inc.
K
Korhan Sevinç
TOBB University of Economics and Technology
B
Burak Aktas
Roketsan Inc.