SOURCE-LINKED INTELLIGENCE

Learning What to Share and What to Personalize: Hierarchical Strategy Co-Evolution for Agent Memory

arXiv · AI, language, vision and robotics · article · Aug 26, 2026 · UTC

Memory-augmented agents maintain compact user profiles throughout extended conversations, enabling personalized and consistent responses without the need to process the entire dialogue history. The quality of these user profiles relies on the underlying memory management strategy: at each step, the agent must determine what to retain, compress, or discard. However, existing methods typically employ a static, one-size-fits-all strategy established before training. In practice, the optimal memory decision is inherently user-specific and dynamically evolves alongside policy optimization. To addre

Read original source ↗ Open in workspace

recordType

paper

region

Global