AI RESEARCH
NaviRAG: Towards Active Knowledge Navigation for Retrieval-Augmented Generation
arXiv CS.CL
•
ArXi:2604.12766v1 Announce Type: new Retrieval-augmented generation (RAG) typically relies on a flat retrieval paradigm that maps queries directly to static, isolated text segments. This approach struggles with complex tasks that require the conditional retrieval and dynamic synthesis of information across different levels of granularity (e.g., from broad concepts to specific evidence). To bridge this gap, we