研究库 论文知识库

内容库 / 论文

arXiv:2609.17012 · RAG 检索增强

ORDER: Task-Conditioned Routing for Retrieval-Augmented Generation

ORDER: Task-Conditioned Routing for Retrieval-Augmented Generation

类型：arxiv
标识：2609.17012
链接：http://arxiv.org/abs/2609.17012v1
主分类：rag
形态：method
TLDR：Retrieval-Augmented Generation (RAG) pipelines typically rely on a fixed indexing and retrieval configuration determined at preprocessing time. This one-size-fits-all design is ill-suited to domain-expert settings, where heterogeneous queries require different chunking granularities, metadata constraints, and source-selection strategies. As a result, configurations that are effective for one family of queries often perform poorly for others. In this paper, we introduce ORDER (Optimal Routing for Dynamic Evidence Retrieval), a query-conditioned RAG framework that jointly adapts indexing and ret
待LLM分类：否
来源文件：
/inbox/tom/_candidates/2026-09-16-agent-rag-longcontext-candidates.json

相关 · 按语义匹配

仓库 griver/Q-RAG

笔记精读：Scaling Beyond Context — 多模态 RAG for Document Understanding Survey

笔记 2026-07-04 上午多模态对照精读 · Seeker（文本→像素的长上下文 MLLM）

笔记 2026-07-03 轻量精读：Qwen-Image-Agent × The Verification Horizon

笔记 Tom 文献雷达 · Agent / RAG / 长上下文 · 2026-08-17 20:40 UTC

文档 Tom-on-flyP-2026-07-16

arXiv

2609.17012

TLDR

Retrieval-Augmented Generation (RAG) pipelines typically rely on a fixed indexing and retrieval configuration determined at preprocessing time. This one-size-fits-all design is ill-suited to domain-expert settings, where heterogeneous queries require different chunking granularities, metadata constraints, and source-selection strategies. As a result, configurations that are effective for one family of queries often perform poorly for others. In this paper, we introduce ORDER (Optimal Routing for Dynamic Evidence Retrieval), a query-conditioned RAG framework that jointly adapts indexing and ret

arXiv ↗ 中文全文