{"version":1,"type":"story","url":"https://digestai.news/story/ragcompass-routes-retrievers-by-reranking-passages-improves-answer-f1","json":"https://digestai.news/story/ragcompass-routes-retrievers-by-reranking-passages-improves-answer-f1.json","markdown":"https://digestai.news/story/ragcompass-routes-retrievers-by-reranking-passages-improves-answer-f1.md","slug":"ragcompass-routes-retrievers-by-reranking-passages-improves-answer-f1","headline":"RAGCompass routes retrievers by reranking passages, improves answer F1 by 28%","summary":"Researchers introduced RAGCompass, a retriever routing method that reads retrieved passages directly instead of relying on query-only features. The approach contrastively fine-tunes a reranker against the answers each evidence set produces, with a small comparison head adding further improvement. Neither component uses retriever-specific parameters.\n\nIn experiments, RAGCompass improved answer F1 by 28% relative to the best fixed retriever. It outperformed fusion baselines, three query-only routers, and a prompted 8B language model. Under generalization tests with unseen corpora, retrievers, or readers, RAGCompass retained most of its gain while query-only baselines fell to or below the best fixed retriever.","keyPoints":["RAGCompass routes retrievers by reranking retrieved passages, not query features","Improves answer F1 by 28% relative to best fixed retriever","Retains most gain on unseen corpus, retriever, or reader"],"whyItMatters":"A generalizable router that works with unseen retrievers and corpora could make RAG systems more robust without retraining for each new data source.","category":{"slug":"research","name":"Research","url":"https://digestai.news/category/research"},"entities":{"companies":[],"models":["RAGCompass"],"people":[]},"firstPublishedAt":"2026-11-05T05:00:00Z","updatedAt":"2026-11-05T05:00:00Z","sourceCount":1,"hasPrimarySource":true,"sources":[{"outlet":"arXiv cs.CL","title":"RAGCompass: Generalizable Retriever Routing via Reranking","url":"https://arxiv.org/abs/2611.05596","publishedAt":"2026-11-05T05:00:00Z","type":"primary","primary":true,"lead":true}],"sourceNotes":null,"discussions":[],"thread":null,"cite":{"text":"Digest AI, \"RAGCompass routes retrievers by reranking passages, improves answer F1 by 28%\", 5 November 2026, https://digestai.news/story/ragcompass-routes-retrievers-by-reranking-passages-improves-answer-f1","publisher":"Digest AI","title":"RAGCompass routes retrievers by reranking passages, improves answer F1 by 28%","datePublished":"2026-11-05T05:00:00Z","url":"https://digestai.news/story/ragcompass-routes-retrievers-by-reranking-passages-improves-answer-f1"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse"}