AI RESEARCH
Mnemis: Dual-Route Retrieval on Hierarchical Graphs for Long-Term LLM Memory
arXiv CS.CL
•
ArXi:2602.15313v2 Announce Type: replace AI Memory, specifically how models organizes and retrieves historical messages, becomes increasingly valuable to Large Language Models (LLMs), yet existing methods (RAG and Graph-RAG) primarily retrieve memory through similarity-based mechanisms. While efficient, such System-1-style retrieval struggles with scenarios that require global reasoning or comprehensive coverage of all relevant information.