AtomMem : Learnable Dynamic Agentic Memory with Atomic Memory Operation

ArXi:2601.08323v3 Announce Type: replace Equipping agents with memory is essential for solving real-world long-horizon problems. However, most existing agent memory mechanisms rely on static and hand-crafted workflows. This limits the performance and generalization ability of these memory designs, which highlights the need for a flexible, learning-based memory framework. In this paper, we propose AtomMem, which reframes memory management as a dynamic decision-making problem.