AI RESEARCH
MemPrivacy: Privacy-Preserving Personalized Memory Management for Edge-Cloud Agents
arXiv CS.CL
•
ArXi:2605.09530v2 Announce Type: replace-cross As LLM-powered agents are increasingly deployed in edge-cloud environments, personalized memory has become a key enabler of long-term adaptation and user-centric interaction. However, cloud-assisted memory management exposes sensitive user information, while existing privacy protection methods typically rely on aggressive masking that removes task-relevant semantics and consequently degrades memory utility and personalization quality.