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 more flexible, learning-based memory framework. In this paper, we propose AtomMem, which reframes memory management as a dynamic decision-making problem. We deconstruct high-level memory processes into fundamental atomic CRUD (Create, Read, Update, Delete) operations, transforming the memory workflow into a learnable decision process. By combining supervised fine-tuning with reinforcement learning, AtomMem learns an autonomous, task-aligned policy to orchestrate memory behaviors tailored to specific task demands. Experimental results across 3 long-context benchmarks demonstrate that the trained AtomMem-8B consistently outperforms prior static-workflow memory methods. Further analysis of training dynamics shows that our learning-based formulation enables the agent to discover structured, task-aligned memory management strategies, highlighting a key advantage over predefined routines.

翻译：为智能体配备记忆对于解决现实世界中的长时程问题至关重要。然而，现有的大多数智能体记忆机制依赖于静态的、手工设计的工作流程。这限制了这些记忆设计的性能和泛化能力，突显了对更灵活、基于学习的记忆框架的需求。本文提出AtomMem，它将记忆管理重新定义为动态决策问题。我们将高级记忆过程解构为基本的原子CRUD（创建、读取、更新、删除）操作，从而将记忆工作流转化为可学习的决策过程。通过结合监督微调与强化学习，AtomMem学习一种自主的、与任务对齐的策略，以编排适应特定任务需求的记忆行为。在3个长上下文基准测试上的实验结果表明，训练后的AtomMem-8B模型始终优于先前的静态工作流记忆方法。对训练动态的进一步分析表明，我们基于学习的框架使智能体能够发现结构化的、与任务对齐的记忆管理策略，这凸显了其相对于预定义流程的关键优势。