2605.30029v1 May 28, 2026 cs.AI

RAISE: RAG Design as an Architecture Search Problem

Zhen Chen
Zhen Chen
Citations: 15
h-index: 2
Weihao Xie
Weihao Xie
Citations: 1
h-index: 1
Peilin Chen
Peilin Chen
Citations: 284
h-index: 10
Shiqi Wang
Shiqi Wang
Citations: 8
h-index: 2
Yuci Liang
Yuci Liang
Citations: 53
h-index: 3
Yibing Liu
Yibing Liu
Citations: 15
h-index: 2

Retrieval-augmented generation (RAG) systems expose numerous design choices spanning query rewriting, chunking, retrieval depth, reranking, and context compression. In practice, these choices are often configured through heuristics, hindering systematic evaluation and reproducibility across settings. We argue that this challenge is best formulated as RAG architecture search. To support controlled and reproducible study of this problem, we introduce the RAG Intelligence Search Engine (RAISE), a comprehensive framework and benchmark for RAG hyperparameter optimization, which evaluates optimization methods for RAG pipelines under standardized search spaces and budgets. RAISE implements 13 search algorithms and evaluates them across seven public text and multimodal datasets using three random seeds. Our experiments show that optimization performance is highly task-dependent: methods that perform strongly on one dataset may not generalize consistently across others, cautioning against interpreting aggregate rankings as evidence of universally superior strategies. RAISE provides a common experimental substrate for fair, reproducible, and systematic research on RAG hyperparameter optimization.

0 Citations
0 Influential
5 Altmetric
25.0 Score
Original PDF

No Analysis Report Yet

This paper hasn't been analyzed by Gemini yet.

Log in to request an AI analysis.

댓글

댓글을 작성하려면 로그인하세요.

아직 댓글이 없습니다. 첫 번째 댓글을 남겨보세요!