Large Language Models (LLMs) excel at many reasoning tasks but struggle with knowledge-intensive queries due to their inability to dynamically access up-to-date or domain-specific information. Retrieval-Augmented Generation (RAG) has emerged as a promising solution, enabling LLMs to ground their responses in external sources. However, existing RAG methods lack fine-grained control over both the query and source sides, often resulting in noisy retrieval and shallow reasoning. In this work, we introduce DeepSieve, an agentic RAG framework that incorporates information sieving via LLM-as-a-knowledge-router. DeepSieve decomposes complex queries into structured sub-questions and recursively routes each to the most suitable knowledge source, filtering irrelevant information through a multi-stage distillation process. Our design emphasizes modularity, transparency, and adaptability, leveraging recent advances in agentic system design. Experiments on multi-hop QA tasks across heterogeneous sources demonstrate improved reasoning depth, retrieval precision, and interpretability over conventional RAG approaches. Our codes are available at https://github.com/MinghoKwok/DeepSieve.

翻译：大型语言模型（LLMs）在许多推理任务中表现出色，但由于无法动态获取最新或特定领域的信息，在处理知识密集型查询时仍面临困难。检索增强生成（RAG）作为一种有前景的解决方案应运而生，它使LLMs能够基于外部信息源生成回答。然而，现有的RAG方法缺乏对查询端和源端的细粒度控制，常常导致检索结果噪声大且推理过程浅层化。本研究提出DeepSieve——一种基于LLM作为知识路由器的智能RAG框架，通过信息筛选机制实现精细化知识处理。DeepSieve将复杂查询分解为结构化子问题，通过多阶段蒸馏过程过滤无关信息，并将每个子问题递归路由至最适配的知识源。该框架设计强调模块化、透明性与可适应性，充分利用了智能体系统设计的最新进展。在跨异构知识源的多跳问答任务上的实验表明，相较于传统RAG方法，本框架在推理深度、检索精度与可解释性方面均有显著提升。相关代码已开源：https://github.com/MinghoKwok/DeepSieve。