让大模型学会动态管理记忆，提升任务迁移能力。
Learning How to Remember: A Meta-Cognitive Management Method for Structured and Transferable Agent Memory
- 用可学习的‘记忆管家’控制记忆的抽象与复用方式。
- 在多个环境中实现性能提升与跨任务迁移，尤其在分布外场景表现更好。
- 适合需要长期决策和知识复用的智能体系统研究者。
大型语言模型代理越来越多地依赖累积记忆来解决长时程决策任务。然而，现有方法通常以固定表示存储记忆，并在单一或隐式抽象层级上重用，限制了泛化能力，且在分布偏移时易导致负向迁移。本文提出元认知记忆抽象方法（MCMA），将记忆抽象视为可学习的认知技能而非固定设计。MCMA通过冻结任务模型与可学习的记忆协管员结合，实现任务执行与记忆管理解耦。记忆协管员采用直接偏好优化训练，决定记忆的结构、抽象及复用策略。记忆被组织成多层抽象层次，支持基于任务相似性的选择性复用。当无可用记忆可转移时，MCMA通过传递记忆协管员实现抽象与管理能力的迁移。在ALFWorld、ScienceWorld和BabyAI上的实验表明，该方法在性能、分布外泛化和跨任务迁移方面均显著优于多个基线。
原文摘要 · Abstract (English)
Large language model (LLM) agents increasingly rely on accumulated memory to solve long-horizon decision-making tasks. However, most existing approaches store memory in fixed representations and reuse it at a single or implicit level of abstraction, which limits generalization and often leads to negative transfer when distribution shift. This paper proposes the Meta-Cognitive Memory Abstraction method (MCMA), which treats memory abstraction as a learnable cognitive skill rather than a fixed design choice. MCMA decouples task execution from memory management by combining a frozen task model with a learned memory copilot. The memory copilot is trained using direct preference optimization, it determines how memories should be structured, abstracted, and reused. Memories are further organized into a hierarchy of abstraction levels, enabling selective reuse based on task similarity. When no memory is transferable, MCMA transfers the ability to abstract and manage memory by transferring the memory copilot. Experiments on ALFWorld, ScienceWorld, and BabyAI demonstrate substantial improvements in performance, out-of-distribution generalization, and cross-task transfer over several baselines.
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。