AI RESEARCH

EvolveMem:Self-Evolving Memory Architecture via AutoResearch for LLM Agents

arXiv CS.LG

ArXi:2605.13941v1 Announce Type: new Long-term memory is essential for LLM agents that operate across multiple sessions, yet existing memory systems treat retrieval infrastructure as fixed: d content evolves while scoring functions, fusion strategies, and answer-generation policies remain frozen at deployment. We argue that truly adaptive memory requires co-evolution at two levels: the d knowledge and the retrieval mechanism that queries it.