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.
Theoretical analysis
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.
Experiment results
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.