cs.CLNov 3, 2026

RAGCompass: Generalizable Retriever Routing via Reranking

Authors: Valentin Six, Mufei Li, Dongqi Fu, Yinglong Xia, Hong Li, Pan Li

Organizations: University of Virginia · Georgia Institute of Technology · Meta

Abstract

Different retrievers exist for retrieval-augmented generation, yet none performs best for all queries. Therefore, the key question is: given a query and retrieved passages from different retrievers, which one is most suited for that query? Existing routers usually make predictions from query-specific features and a fixed pool of retrievers; such routers have no output for an unseen retriever and are incapable by design on a new corpus. To fill these gaps, RAGCompass reads the retrieved passage sets themselves: passages from an unfamiliar retriever or corpus stay directly comparable to other passages, so routing stays well designed where a query-only map would fail. We contrastively fine-tune a reranker against the answer each evidence set produces, which accounts for most of the gain; a small comparison head adds a moderate improvement, and neither component has retriever-specific parameters. RAGCompass improves answer F1 by 28% relative to the best fixed retriever, and outperforms fusion baselines, three query-only routers, and a prompted 8B language model. Generalization experiments show that RAGCompass keeps most of its gain under an unseen corpus, retriever, or reader, while query-only baselines fall to the best fixed retriever or below.

Figures & tables

Appendix figures & tables9 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Revisiting RAG Retrievers: An Information Theoretic Benchmark

    Feb 25, 2026Wenqing Zheng, Dmitri Kalaev, Noah Fatsi +5RAG EvaluationIR Evaluation

  2. Retriever Portfolios: A Principled Approach to Adaptive RAG

    May 29, 2026Miltiadis Stouras, Vincent Cohen-Addad, Silvio Lattanzi +1Retrieval-Augmented GenerationAdaptive RAG

  3. Retriever-Free Retrieval: Navigating Documents with Decision Models

    Oct 26, 2026Chao Wan, Paul Jünger, Beixi Du +3Knowledge Retrieval in Language ModelsInformation Retrieval