{"ID":2882628,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.09497","arxiv_id":"2508.09497","title":"From Ranking to Selection: A Simple but Efficient Dynamic Passage Selector for Retrieval Augmented Generation","abstract":"Retrieval-augmented generation (RAG) systems are often bottlenecked by their reranking modules, which typically score passages independently and select a fixed Top-K size. This approach struggles with complex multi-hop queries that require synthesizing evidence across multiple documents, creating a trade-off where small K values omit crucial information and large K values introduce noise. To address this, we introduce the Dynamic Passage Selector (DPS), a novel reranking framework that treats passage selection as a supervised learning problem. Unlike traditional point-wise or list-wise methods, DPS is fine-tuned to capture inter-passage dependencies and dynamically select the most relevant set of passages for generation. As a seamless plug-and-play module, DPS requires no modifications to the standard RAG pipeline. Comprehensive evaluations on five benchmarks show that DPS consistently outperforms state-of-the-art rerankers and fine-tuning methods. Notably, on the challenging MuSiQue dataset, DPS improves the F1-score by 30.06% and 15.4% over strong baselines like Qwen3-reranker and RankingGPT, respectively. Our results demonstrate that by enabling adaptive evidence selection, DPS substantially enhances reasoning capabilities in complex RAG scenarios.","short_abstract":"Retrieval-augmented generation (RAG) systems are often bottlenecked by their reranking modules, which typically score passages independently and select a fixed Top-K size. This approach struggles with complex multi-hop queries that require synthesizing evidence across multiple documents, creating a trade-off where smal...","url_abs":"https://arxiv.org/abs/2508.09497","url_pdf":"https://arxiv.org/pdf/2508.09497v1","authors":"[\"Siyuan Meng\",\"Junming Liu\",\"Yirong Chen\",\"Song Mao\",\"Pinlong Cai\",\"Guohang Yan\",\"Botian Shi\",\"Ding Wang\"]","published":"2025-08-13T05:05:34Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\"]","methods":"[\"RAG\"]","has_code":false}