HyperGraphPro: Progress-Aware Reinforcement Learning for Structure-Guided Hypergraph RAG

ArXi:2601.17755v2 Announce Type: replace Graph Retrieval-Augmented Generation (GraphRAG) has emerged as a promising paradigm that organizes external knowledge into structured graphs of entities and relations, enabling large language models (LLMs) to perform complex reasoning beyond text-chunk retrieval. Recent advances have integrated reinforcement learning (RL) into agentic GraphRAG approaches, enabling iterative interactions with knowledge graphs during