发表机构
Beijing Academy of Artificial Intelligence; University of Chinese Academy of Sciences; Institute of Software, Chinese Academy of Sciences; National University of Defense Technology（北京人工智能研究院; 中国科学院大学; 中国科学院软件研究所; 国防科技大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对LLM智能体长期记忆中临时信息覆盖持久知识的问题，提出生命周期感知的记忆框架LifeFuse-Mem，通过分离稳定与瞬态知识减少覆盖，提升保留率并保持竞争力。
AI 中文摘要
长时间运行的LLM智能体需要记忆机制来在交互过程中维持连贯的内部状态。我们研究了一种带有生命周期标签的记忆设置，其中写入事件在训练期间提供生命周期元数据，并在评估期间使用阶段感知的读取。这种设置反映了区分应在未来交互中保持影响力的信息与仅应影响当前上下文的信息的需求。这些生命周期之间的不匹配可能导致临时信息覆盖持久知识，从而导致持久智能体中的行为漂移。在此设置中，我们引入了\ extbf{LifeFuse-Mem}，一种生命周期感知的神经记忆框架，根据时间承诺分离信息。LifeFuse-Mem使用专用的记忆组件和生命周期感知的更新，使稳定和瞬态知识得以局部演化，而不会将临时上下文转换为持久状态。在受控的抗覆盖基准上，LifeFuse-Mem提高了获取控制的保留率并减少了临时覆盖；在两个公共长记忆基准上，它保持广泛的竞争力。这些结果表明，显式的生命周期信号可以帮助诊断和缓解紧凑在线记忆中的覆盖问题。
英文摘要
Long-running LLM agents require memory mechanisms that maintain coherent internal states across interactions. We study a lifecycle-labeled memory setting in which write episodes provide lifecycle metadata during training, and phase-aware readout is used during evaluation. This setting reflects the need to distinguish information that should remain influential across future interactions from information that should affect only the current context. A mismatch between these lifecycles can cause temporary information to overwrite durable knowledge, leading to behavioral drift in persistent agents. Within this setting, we introduce \textbf{LifeFuse-Mem}, a lifecycle-aware neural memory framework that separates information according to its temporal commitment. LifeFuse-Mem uses dedicated memory components and lifecycle-aware updates to allow stable and transient knowledge to evolve locally without converting temporary context into durable state. On the controlled anti-overwrite benchmark, LifeFuse-Mem improves acquisition-controlled retention and reduces temporary overwrite; on two public long-memory benchmarks, it remains broadly competitive. These results suggest that explicit lifecycle signals can help diagnose and mitigate overwrite in compact online memory.
