ArchRAG: Attributed Community-based Hierarchical Retrieval-Augmented Generation

By Shu Wang, Yixiang Fang, Ying-Li Zhou, Xi-Lin Liu, Yuchi Ma. 2025

Subfields: Retrieval-Augmented Generation, Graph Learning, Knowledge Graphs & Representation

Citations in the corpus

• ASTRA-QA: A Benchmark for Abstract Question Answering over Documents (2026, unknown): “Recent RAG methods [2–4, 7, 24, 25] have moved further toward long-form and document-level synthesis through hierarchical retrieval, graph-structured indexing, and long-context reading.”
• MG2-RAG: Multi-Granularity Graph for Multimodal Retrieval-Augmented Generation (2026, unknown): “Given the high computational cost of graph construction, subsequent research has focused on scalable indexing strategies, including dual-level retrieval [23], bipartite or relation-free graph designs [34,80], and hierarchical tree-based structures [67,77].”