AI RESEARCH

GAAMA: Graph Augmented Associative Memory for Agents

arXiv CS.AI

ArXi:2603.27910v1 Announce Type: new AI agents that interact with users across multiple sessions require persistent long-term memory to maintain coherent, personalized behavior. Current approaches either rely on flat retrieval-augmented generation (RAG), which loses structural relationships between memories, or use memory compression and vector retrieval that cannot capture the associative structure of multi-session conversations.