---
title: "RAGCompass: Generalizable Retriever Routing via Reranking"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2611.05596v1"
permalink: "https://feed.astralor.com/items/itm_67189d3776cd63300c3a6e1d"
published: "2026-11-03T20:36:24.000Z"
score: 57
channel: "ai"
tags: ["RAG","RAGCompass","Generalizable Retriever Routing","Reranking Different","Therefore","Different","Existing"]
---

# RAGCompass: Generalizable Retriever Routing via Reranking

## At a glance

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 su…

## Key points

- 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.

## Full text

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.

---

Verify against the original before citing; curated by Astral Feed: https://feed.astralor.com/items/itm_67189d3776cd63300c3a6e1d