Hierarchical Abstract Tree for Cross-Document Retrieval-Augmented Generation

ArXi:2605.00529v1 Announce Type: cross Retrieval-augmented generation (RAG) enhances large language models with external knowledge, and tree-based RAG organizes documents into hierarchical indexes to queries at multiple granularities. However, existing Tree-RAG methods designed for single-document retrieval face critical challenges in scaling to cross-document multi-hop questions: (1) poor distribution adaptability, where $k$-means clustering