arXiv:2601.19935cs.CLcs.AI2026-01ACL被引 26

评测智能体如何主动用长期记忆完成任务,发现现有系统仍不达标。

Mem2ActBench: A Benchmark for Evaluating Long-Term Memory Utilization in Task-Oriented Autonomous Agents

  • 构建模拟长期交互的基准,测试智能体主动调用记忆执行任务的能力。
  • 生成400个强依赖记忆的任务,91.3%经人工验证需记忆支持。
  • 揭示当前记忆框架在参数定位上表现不足,适合评估智能体记忆应用能力。

基于大语言模型的智能体在复杂工具型任务中越来越依赖长期记忆以驱动行动。然而,现有基准主要测试智能体被动检索孤立事实的能力,无法评估其主动运用记忆执行任务的核心能力。为此,我们提出 extsc{Mem2ActBench},一个评估智能体能否通过选择合适工具并准确设置参数,主动利用长期记忆完成任务的基准。该基准模拟持久助理场景:用户在长时间、中断的交互中反复提及同一主题,期望先前建立的偏好和任务状态能被隐式延续。数据集通过自动化流水线整合异构来源(ToolACE、BFCL、Oasst1),借助一致性建模解决冲突,生成2,029个会话,平均包含12轮用户-助手-工具交互。基于这些记忆链,逆向生成方法构建400个工具使用任务,经人工评估确认其中91.3%具有强记忆依赖性。对七种记忆框架的实验表明,当前系统在主动应用记忆进行参数定位方面仍严重不足,凸显了改进记忆应用评估与实现的迫切需求。

原文摘要 · Abstract (English)

Large Language Model (LLM)-based agents are increasingly deployed for complex, tool-based tasks where long-term memory is critical to driving actions. Existing benchmarks, however, primarily test a angent's ability to passively retrieve isolated facts in response to explicit questions. They fail to evaluate the more crucial capability of actively applying memory to execute tasks. To address this gap, we introduce \textsc{Mem2ActBench}, a benchmark for evaluating whether agents can proactively leverage long-term memory to execute tool-based actions by selecting appropriate tools and grounding their parameters. The benchmark simulates persistent assistant usage, where users mention the same topic across long, interrupted interactions and expect previously established preferences and task states to be implicitly applied. We build the dataset with an automated pipeline that merges heterogeneous sources (ToolACE, BFCL, Oasst1), resolves conflicts via consistency modeling, and synthesizes 2,029 sessions with 12 user--assistant--tool turns on average. From these memory chains, a reverse-generation method produces 400 tool-use tasks, with human evaluation confirming 91.3\% are strongly memory-dependent. Experiments on seven memory frameworks show that current systems remain inadequate at actively utilizing memory for parameter grounding, highlighting the need for more effective approaches to evaluate and improve memory application in task execution.

长期记忆智能体评测任务执行

Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品;中文卡片由大模型生成,请以原文为准。