Researchers from the University of Minnesota have introduced GNN-RAG, a novel AI method that combines the language understanding abilities of Large Language Models (LLMs) with the reasoning abilities of Graph Neural Networks (GNNs) in a Retrieval-Augmented Generation (RAG) style. This approach aims to enhance the efficiency and performance of RAG, achieving state-of-the-art (SOTA) results that outperform or match GPT-4. Additionally, Ant Group has proposed MetRag, a multi-layered thoughts enhanced retrieval augmented generation framework. These advancements highlight the ongoing relevance and innovation in the field of AI, particularly in enhancing the capabilities of LLMs and GNNs. A comprehensive guide on how RAG helps Transformers to build customizable Large Language Models is also available.