The framework uses reinforcement learning to choose when to retrieve information from text and graphs during reasoning, with a reward that discourages unnecessary searches.
RouteRAG is a retrieval-augmented generation (RAG) framework that uses reinforcement learning to train a model to choose retrieval actions across text and graphs during reasoning. It adds an efficiency reward to discourage unnecessary searches.
The approach aims to balance answer correctness with the cost of querying graph data. If you use AI to study or apply this idea, avoid entering personal or confidential information; also check responses and sources before relying on them.