AI RESEARCH
From Volume to Value: Preference-Aligned Memory Construction for On-Device RAG
arXiv CS.LG
•
ArXi:2605.18271v1 Announce Type: cross With the rapid emergence of personal AI agents based on Large Language Models (LLMs), implementing them on-device has become essential for privacy and responsiveness. To handle the inherently personal and context-dependent nature of real-world requests, such agents must ground their generation in device-resident personal context. However, under tight memory budgets, the core bottleneck is what to so that retrieval remains aligned with the user.