让大模型记忆像人脑一样自动更新，通过快慢变量协同实现持续学习。
Continual Knowledge Updating in LLM Systems: Learning Through Multi-Timescale Memory Dynamics
- 用快慢变量耦合机制模拟生物记忆，构建动态关联图
- 新知识即时可用，重复强化，无关信息自然遗忘
- 适合关注长期学习与记忆演化的研究者
大模型训练一次后便部署于不断变化的世界中。外部记忆可弥补此缺陷，但多数系统仍需人工管理，无法自主适应。生物记忆则不同：多时间尺度的耦合动力学使新联结即刻可用，重复确认后逐步巩固，其余逐渐消退。本文主张外部记忆应遵循类似原理。在Memini中，这一理念体现为一种关联记忆系统，将知识组织为有向图。每条边包含一对耦合的内部变量，一快一慢，遵循Benna-Fusi突触巩固模型。这种耦合使得情景敏感性、渐进巩固与选择性遗忘成为单一机制的自然表现，将外部记忆重新定义为可通过自身动态重构的学习基底。本文为无实验评估的早期概念设计。
原文摘要 · Abstract (English)
LLMs are trained once, then deployed into a world that never stops changing. External memory compensates for this, but most systems manage it explicitly rather than letting it adapt on its own. Biological memory works differently: coupled multi-timescale dynamics make new associations immediately usable, strengthen what repetition confirms, and let the rest fade. We argue that external memory should follow a similar principle. In Memini, this view takes the form of an associative memory that organizes knowledge as a directed graph. Each edge carries two coupled internal variables, one fast and one slow, following the Benna-Fusi model of synaptic consolidation. From this coupling, episodic sensitivity, gradual consolidation, and selective forgetting are expected to emerge as facets of a single mechanism, reframing external memory as a learning substrate that reorganizes through its own dynamics. This workshop article describes an early-stage conceptual design without experimental evaluation.
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。