Rethinking Retrieval-Augmented Generation as a Cooperative Decision-Making Problem

ArXi:2602.18734v2 Announce Type: replace-cross Retrieval-Augmented Generation (RAG) has nstrated strong effectiveness in knowledge-intensive tasks by grounding language generation in external evidence. Despite its success, many existing RAG systems are built based on a ranking-centric, asymmetric dependency paradigm, where the generation quality of the generator is highly dependent on reranking results of the reranker.