---
id: 20261106-T0-07
title: "RAGCompass：用重排序为每个查询选择最合适的检索器"
title_en: "RAGCompass Routes Queries to the Best Retriever via Reranking"
url: https://ai.daily.yangsir.net/daily/20261106-T0-07
issue_date: 2026-11-06
publish_date: 2026-11-05T05:00:00.000Z
category: research
source_name: "arXiv cs.CL (NLP)"
source_url: https://arxiv.org/abs/2611.05596
---

# RAGCompass：用重排序为每个查询选择最合适的检索器

不同检索器在RAG中各有擅长，没有一种能对所有查询都表现最好。RAGCompass针对"给定查询和多路检索结果，该选哪一个"的问题，用重排序信号做检索器路由，并能泛化到未见过的检索器组合。具体指标原文未给出。实际影响：RAG系统可按查询动态切换检索器，减少固定单一检索器带来的效果损失。

## English Version

**RAGCompass Routes Queries to the Best Retriever via Reranking**

Retrieval-augmented generation systems often rely on multiple retrievers, but no single retriever wins on every query. RAGCompass addresses the routing question: given a query and passages retrieved by different retrievers, which retriever suits it best? The method routes queries using reranking signals and is designed to generalize across retriever combinations. The abstract does not report specific benchmark numbers. Practical impact: RAG pipelines can pick a retriever per query instead of locking into one, avoiding the accuracy loss of a fixed choice.

---

**来源**：[arXiv cs.CL (NLP)](https://arxiv.org/abs/2611.05596)

**详情页**：https://ai.daily.yangsir.net/daily/20261106-T0-07

---

*智语观潮 · Daily — https://ai.daily.yangsir.net/llms.txt*