We propose a novel RAG framework in which a retriever and an LLM cooperate to exchange knowledge, and the retriever utilizes information of both earlier and later layers to accurately rank documents relevant to a question.

Training LLMs to combine reasoning with external knowledge retrieval via RL without any supervised data on reasoning steps.

NeuroPath is a RAG framework inspired by brain path navigation. It tracks semantic paths and refines retrieval via LLM reasoning, enhancing semantic coherence and reducing noise, achieves state-of-the-art performance on multi-hop QA.