English

R$^3$AG: Retriever Routing for Retrieval-Augmented Generation

Information Retrieval 2026-04-28 v1

Abstract

Retrieval-augmented generation (RAG) has become a cornerstone for knowledge-intensive tasks. However, the efficacy of RAG is often bottlenecked by the ``one-size-fits-all'' retrieval paradigm, as different queries exhibit distinct preferences for different retrievers. While recent routing techniques attempt to select the optimal retriever dynamically, they typically operate under a ``single and static capability'' assumption, selecting retrievers solely based on semantic relevance. This overlooks a critical distinction in RAG: a retrieved document must not only be relevant but also effectively support the generator in producing correct answers. To address this limitation, we propose R3^3AG, a novel routing framework that explicitly models the dynamic alignment between queries and retriever capabilities. Unlike previous approaches, R3^3AG decomposes retriever capability into two learnable dimensions: retrieval quality and generation utility. We employ a contrastive learning objective that leverages complementary supervision signals, \textit{i.e.}, document assessments and downstream answer correctness, to capture query-specific preference shifts. Extensive experiments on several knowledge-intensive tasks show that R3^3AG consistently outperforms both the best individual retrievers and state-of-the-art static routing methods.

Keywords

Cite

@article{arxiv.2604.22849,
  title  = {R$^3$AG: Retriever Routing for Retrieval-Augmented Generation},
  author = {Tong Zhao and Yutao Zhu and Yucheng Tian and Zhicheng Dou},
  journal= {arXiv preprint arXiv:2604.22849},
  year   = {2026}
}
R2 v1 2026-07-01T12:34:17.470Z