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
• 被引：0
• 被引来源：Semantic Scholar + OpenAlex
• S2被引：0
• OpenAlex被引：0
• 影响力被引：0
• 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
• OpenAlex ID：W7213420787
• OpenAlex DOI：10.48550/arxiv.2609.17012
• DOI：10.48550/arxiv.2609.17012
• DOI来源：OpenAlex
• 开放获取：green
• 开放获取链接：https://doi.org/10.48550/arxiv.2609.17012
• OpenAlex更新：2026-09-18
• 待LLM分类：否
• 标题中文：ORDER：面向检索增强生成的任务条件化路由。
• TLDR中文：检索增强生成（RAG）管线通常依赖在预处理阶段确定的固定索引与检索配置。这种一刀切的设计难以适配领域专家场景，因为异构查询需要不同的分块粒度、元数据约束与来源选择策略。因此，针对某一类查询有效的配置，往往在其他类查询上表现欠佳。本文提出 ORDER（Optimal Routing for Dynamic Evidence Retrieval），一种查询条件化的 RAG 框架，可联合自适应地调整索引与……
• 来源文件：
• /inbox/tom/_candidates/2026-09-16-agent-rag-longcontext-candidates.json
• [OpenAlex backfill]
• [S2 enrich]