探索智能体记忆系统的跨场景通用性：诊断与强基线
Exploring Cross-Scenario Generality of Agentic Memory Systems: Diagnostics and a Strong Baseline
AI总结：
通过诊断现有记忆系统在多种场景下的表现，提出一个基于工具调用的自管理记忆框架AutoMEM，实现最佳跨场景通用性。
摘要：
LLM智能体积累的历史记录会超出其上下文窗口，这推动了关于记忆系统的研究日益增多。然而，大多数现有设计仅针对单一场景（多会话聊天或单轨迹格式）进行调优，几乎没有证据表明它们能够泛化到部署中智能体遇到的异构轨迹。我们重新审视了八个记忆系统以及一个用于搜索问题的智能体框架，在五个场景上进行了评估：单轮问答、多会话聊天、智能体轨迹问答、记忆压力测试和长周期智能体任务。该框架通过工具调用自管理平面文本文件存储，实现了最佳跨任务排名，这表明记忆性能取决于赋予智能体对存储和检索的主动控制，而不是被动地依赖固定流水线后的存储。我们将这一见解实例化为AutoMEM，一个具有自管理工具接口的智能体记忆框架，在我们评估的系统中实现了最佳跨场景通用性。
英文摘要：
LLM agents accumulate histories that outgrow their context windows, motivating a growing literature on memory systems. Yet most existing designs are tuned to a single scenario (multi-session chat or a single trajectory format), and there is little evidence that they generalize across the heterogeneous trajectories agents encounter in deployment. We revisit eight memory systems plus an agentic harness for search problems, on five scenarios: single-turn QA, multi-session chat, agentic-trajectory QA, memory stress tests, and long-horizon agentic tasks. The harness, which self-manages flat text-file storage via tool calls, achieves the best cross-task ranking, suggesting that memory performance hinges on giving the agent active control over storage and retrieval rather than on a passive store behind a fixed pipeline. We instantiate this insight in AutoMEM, an agentic memory harness with a self-managed tool interface that achieves the best cross-scenario generality among the systems we evaluate.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
