KohakuRAG: A simple RAG framework with hierarchical document indexing

ArXi:2603.07612v1 Announce Type: new Retrieval-augmented generation (RAG) systems that answer questions from document collections face compounding difficulties when high-precision citations are required: flat chunking strategies sacrifice document structure, single-query formulations miss relevant passages through vocabulary mismatch, and single-pass inference produces stochastic answers that vary in both content and citation selection.