Stateful Evidence-Driven Retrieval-Augmented Generation with Iterative Reasoning

ArXi:2604.14170v1 Announce Type: cross Retrieval-Augmented Generation (RAG) grounds Large Language Models (LLMs) in external knowledge but often suffers from flat context representations and stateless retrieval, leading to unstable performance. We propose Stateful Evidence-Driven RAG with Iterative Reasoning, a framework that models question answering as a progressive evidence accumulation process.