ActiveMem：面向长时程智能体的动态潜在记忆树
ActiveMem: Dynamic Latent Memory Trees for Long-Horizon Agents
浏览论文内容
中文总结 AI 辅助
ActiveMem提出分层潜在执行树记忆框架，通过依赖感知的递归组织与强化学习动态策略，提升长时程智能体的任务完成度、推理稳定性及记忆效率，并使紧凑开源模型媲美大型专有系统。
中文摘要 AI 辅助
大型语言模型（LLM）智能体日益依赖外部记忆来支持长时程推理与决策。现有记忆系统通常将历史轨迹或摘要作为独立的上下文片段进行检索，忽略了多步执行背后的程序性依赖。随着记忆规模的增长，这种扁平化检索会导致上下文碎片化和跨任务干扰，进而产生结构不一致的推理轨迹。我们提出ActiveMem，一种分层记忆框架，它将智能体经验递归地组织为依赖感知的潜在执行树。ActiveMem将轨迹抽象为可复用的子任务节点，同时显式保留执行转换，从而能够基于当前执行状态进行连贯的推理路径检索。为支持持续适应，ActiveMem进一步通过强化学习学习动态记忆扩展、检索和剪枝策略。在多种智能体基准上的实验表明，与现有基于记忆的智能体相比，ActiveMem在任务完成度、推理稳定性和记忆效率方面均持续提升。此外，ActiveMem使紧凑的开源模型能够达到与规模大得多的专有系统相当的性能。
英文摘要
Large Language Model (LLM) agents increasingly rely on external memory to support long-horizon reasoning and decision making. Existing memory systems typically retrieve historical trajectories or summaries as independent context fragments, overlooking the procedural dependencies underlying multi-step execution. As memory scales, such flat retrieval introduces context fragmentation and cross-task interference, leading to structurally inconsistent reasoning trajectories. We propose ActiveMem, a hierarchical memory framework that recursively organizes agent experiences into dependency-aware latent execution trees. ActiveMem abstracts trajectories into reusable subtask nodes while explicitly preserving execution transitions, enabling coherent reasoning-path retrieval conditioned on the current execution state. To support continual adaptation, ActiveMem further learns dynamic memory expansion, retrieval, and pruning policies through reinforcement learning. Experiments across various agent benchmarks demonstrate that ActiveMem consistently improves task completion, reasoning stability, and memory efficiency over existing memory-based agents. Moreover, ActiveMem enables compact open-weight models to achieve competitive performance with substantially larger proprietary systems.
