DeepRAG, a novel framework for large language models, combines reasoning with retrieval-augmented generation by modeling it as a Markov Decision Process. The system demonstrates a 21.99% improvement in answer accuracy through strategic decomposition of queries and dynamic knowledge retrieval, addressing the challenge of factual hallucinations in LLMs.

https://arxiv.org/abs/2502.01142

via https://hnrss.org/newest?points=100