让大模型学会按人定制记忆策略，提升长期任务表现。
Personalize-then-Store: Benchmarking and Learning Personalized Memory for Long-horizon Agents
- 基于用户行为设计个性化记忆存储门控机制
- 在多用户多领域数据上实现显著记忆保留提升
- 适合需要长期记忆的智能助手与对话系统研究者
现有基于大语言模型的记忆系统采用通用静态策略，忽视了不同用户关注的上下文差异。这种不匹配导致有限记忆预算被临时交互占用，而关键信息未能留存，影响长时任务表现。为此，我们提出一个未被充分探索的问题：大模型能否学习个性化记忆策略？我们构建了首个个性化记忆评估基准PerMemBench，涵盖跨多领域、多年份的多样化用户行为历史。进一步提出会话级存储门控机制，轻量级地跳过无关会话的记忆操作。实验表明，在理想门控条件下个性化可带来显著记忆保留增益，但准确识别何时存储仍是开放且关键挑战。
原文摘要 · Abstract (English)
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 gap, we investigate an underexplored question: can LLM based memory systems learn personalized memory policies? We introduce PerMemBench, the first benchmark for evaluating personalized memory systems, featuring multi year, multi domain interaction histories across diverse user personas. We further present the first empirical study of memory personalization, proposing session level storage gating, a lightweight framework that selectively bypasses memory operations for transient sessions. Our study confirms that personalization yields substantial retention gains under perfect gating, yet reveals that accurate gating remains an open and critical challenge.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。