DeepSieve: Information Sieving via LLM-as-a-Knowledge-Router

TL;DR

DeepSieve is a novel retrieval-augmented generation framework that decomposes complex queries into sub-questions, routing them to appropriate sources for improved reasoning, precision, and interpretability in knowledge-intensive tasks.

Contribution

DeepSieve introduces an agentic RAG framework with information sieving, enabling fine-grained query decomposition and source routing for enhanced reasoning and transparency.

Findings

Improved reasoning depth in multi-hop QA tasks.

Higher retrieval precision over traditional RAG methods.

Enhanced interpretability through modular design.

Abstract

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.