DeepSieve: Information Sieving via LLM-as-a-Knowledge-Router
This addresses the challenge of enhancing LLM performance on complex, knowledge-intensive tasks for users relying on up-to-date or domain-specific information, representing an incremental improvement over existing RAG methods.
The paper tackles the problem of noisy retrieval and shallow reasoning in Retrieval-Augmented Generation (RAG) for knowledge-intensive queries by introducing DeepSieve, an agentic framework that decomposes queries and routes them to suitable sources, resulting in improved reasoning depth, retrieval precision, and interpretability on multi-hop QA tasks.
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.