S2G-RAG: Structured Sufficiency and Gap Judging for Iterative Retrieval-Augmented QA

arXiv:2604.23783v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) grounds language models in external evidence, but multi-hop question answering remains difficult because iterative pipelines must control what to retrieve next and when the available evidence is adequate. In...