LifeMem：实现LLM智能体的终身经验复用
LifeMem: Enabling Lifelong Experience Reuse for LLM Agents
浏览论文内容
中文总结 AI 辅助
针对LLM智能体跨环境经验复用难与灾难性遗忘问题，提出LifeMem终身学习框架，通过聚类轨迹提取技能并检索指导行动，在10个环境、13k+任务上验证了其减少遗忘并提升跨任务迁移的效果。
中文摘要 AI 辅助
大型语言模型智能体被期望在其生命周期中通过复用过去的经验，持续适应新任务和新环境。然而，现有的基于记忆的智能体难以跨环境迁移可复用的经验，并且随着经验的积累会出现灾难性遗忘。为应对这些挑战，我们提出了LifeMem，一个终身学习框架，使智能体能够在多个环境之间迁移知识。在学习过程中，LifeMem基于底层工作流对积累的交互轨迹进行聚类，以提取可复用的技能。在推理时解决新任务时，智能体会回忆相关技能和轨迹来指导行动。为验证我们的方法，我们在10个环境和超过13k个任务上进行了实验，并使用了2k条新标注的交互轨迹。结果表明，LifeMem能够在终身学习中实现有效的经验复用，既减少了对已学任务的遗忘，又实现了优越的跨任务迁移。进一步的分析表明，任务流会影响学习效果，而在记忆中对结构相似的轨迹进行整合能够提升性能。
英文摘要
Large language model agents are expected to continuously adapt to new tasks and environments over their lifetime by reusing past experience. However, existing memory-based agents struggle to transfer reusable experience across environments and suffer from catastrophic forgetting as experience accumulated. To address these challenges, we propose LifeMem, a lifelong learning framework that enables agents to transfer knowledge across multiple environments. During learning, LifeMem clusters accumulated interaction trajectories based on underlying workflows to extract reusable skills. When solving a new task at inference time, the agent recalls relevant skills and trajectories to guide actions. To validate our method, we conduct experiments across 10 environments and over 13k tasks with 2k newly annotated interaction trajectories. Results show that LifeMem enables effective experience reuse in lifelong learning, achieving both reduced forgetting on learned tasks and superior cross-task transfer. Further analysis reveals that task streaming impacts learning, while consolidating structurally similar trajectories within memory boosts performance.
发表机构
- Beijing Institute of Technology（北京理工大学）
- Beihang University（北京航空航天大学）
- Harbin Institute of Technology（哈尔滨工业大学）
- Baidu Inc.（百度公司）
机构由 AI 辅助整理，请以论文原文为准。
