Personalize-then-Store: Benchmarking and Learning Personalized Memory for Long-horizon Agents 事件

Personalize-then-Store: Benchmarking and Learning Personalized Memory for Long-horizon Agents arXiv:2605.25535v1 Announce Type: new Abstract: Existing large language model (LLM) based memory systems apply universal, static policies that overlook a fundamental reality: the contexts that are worth storing in memory are different across users. This misalignment wastes limited memory budget on transient interactions while failing to preserve critical context for long horizon tasks. To address this