HippoRAG is a novel retrieval framework designed to enhance the long-term memory capabilities of large language models (LLMs). Inspired by the hippocampal indexing theory, HippoRAG integrates LLMs, knowledge graphs, and the Personalized PageRank (PPR) algorithm to mimic the roles of the neocortex and hippocampus in human memory. This approach enables deeper and more efficient knowledge integration over new experiences, outperforming existing retrieval-augmented generation (RAG) methods by up to 20% in multi-hop question answering tasks. HippoRAG's single-step retrieval process is significantly faster and cheaper than iterative retrieval methods like IRCoT, while still achieving comparable or better performance. The method also demonstrates the ability to handle complex scenarios that are beyond the reach of current RAG methods, particularly in path-finding multi-hop questions. The paper includes detailed experimental results, comparisons with various baselines, and discussions on the limitations and potential improvements of HippoRAG.HippoRAG is a novel retrieval framework designed to enhance the long-term memory capabilities of large language models (LLMs). Inspired by the hippocampal indexing theory, HippoRAG integrates LLMs, knowledge graphs, and the Personalized PageRank (PPR) algorithm to mimic the roles of the neocortex and hippocampus in human memory. This approach enables deeper and more efficient knowledge integration over new experiences, outperforming existing retrieval-augmented generation (RAG) methods by up to 20% in multi-hop question answering tasks. HippoRAG's single-step retrieval process is significantly faster and cheaper than iterative retrieval methods like IRCoT, while still achieving comparable or better performance. The method also demonstrates the ability to handle complex scenarios that are beyond the reach of current RAG methods, particularly in path-finding multi-hop questions. The paper includes detailed experimental results, comparisons with various baselines, and discussions on the limitations and potential improvements of HippoRAG.