Warm-Start UCB：从延迟单边反馈学习个性化记忆门控
Learning Personalized Memory Gating from Delayed One-Sided Feedback
一篇讲智能体记忆管理的论文，提出 Warm-Start UCB，能按用户学习该记住哪些事实，还带遗憾上界证明。
论文研究语言模型智能体的细粒度记忆门控问题：有限记忆库无法保存所有事实，而现有门控策略在用户间共享，无法适配用户各自的复用模式。作者提出基于检索结果的标注方法，判断某条事实是否被后续检索并纳入回复。他们把在线记忆门控建模为带延迟单边反馈的 contextual apple tasting，提出 Warm-Start UCB 算法，将离线学习与在线适应用户结合。理论分析给出了高概率遗憾上界 Õ(Tε∧d√T)，条件是延迟窗口不超过 O(√T)。实验显示该方法在不同记忆预算和历史长度下均优于所有基线。
Learning Personalized Memory Gating from Delayed One-Sided Feedback
Long-term memory enables language-model agents to personalize future interactions, but a finite memory bank cannot preserve every extracted fact. Existing memory gating policies are typically shared across users and therefore fail to account for user-specific patterns of future reuse. In this paper, we study memory gating at the fact level. We first propose a retrieval-based labeling strategy that labels each fact by whether it is later retrieved and incorporated into responses. We then formulate online memory gating as contextual apple tasting with delayed one-sided feedback, and propose Warm-Start UCB, which combines offline learning from existing data with online adaptation to the current user. Our theoretical analysis establishes a high-probability regret upper bound of $\tilde{O}(Tε\wedge d\sqrt{T})$ when the delay window is at most $O(\sqrt{T})$, where $T$ is the total number of rounds, $ε$ is the initialization error, $d$ is the dimension of the feature map, and $\tilde{O}(\cdot)$ hides constant and poly-logarithmic factors. The results of our experiment demonstrate that our method outperforms all baselines under different memory budgets and history lengths, establishing it as a promising personalized memory gating policy.