系统梳理大模型记忆机制，理清各类方法的差异与联系。
Memory for Large Language Models
- 从表征、更新、持久性三维度构建记忆分类框架
- 揭示计算耦合与独立可寻址记忆的本质区别
- 适合研究大模型架构与记忆设计的学者参考
记忆已演变为大语言模型（LLMs）的基础架构维度，从计算的隐含产物转变为一系列显式、可控制的机制。尽管近期出现多种策略——涵盖瞬时注意力、递归状态动态、参数高效适配及可扩展查找存储——但快速演进导致研究格局高度碎片化。本文提出一种以架构为中心的记忆系统性分类法，从表征（隐式/显式）、更新动态（离线/在线）、持久性（短期/长期）三个正交维度刻画记忆。进一步形式化了记忆写入、路由、状态转换与整合的精细机制。该统一视角厘清了计算耦合与独立可寻址记忆的概念边界，有效弥合不同架构范式间的鸿沟。同时，批判性分析混合记忆架构、系统级效率权衡及多维评估方法。通过将分散进展整合为连贯框架，本综述勾勒出以记忆为中心的LLM设计轨迹，并为未来可扩展、自适应语言建模创新提供原则性基础。
原文摘要 · Abstract (English)
Memory has evolved into a foundational architectural dimension in large language models (LLMs), shifting from an implicit byproduct of computation to a spectrum of explicit, controllable mechanisms. While recent advances introduce diverse strategies---spanning transient attention, recurrent state dynamics, parameter-efficient adaptations, and scalable lookup storage---this rapid evolution has led to a highly fragmented research landscape. In this survey, we present a systematic, architecture-centric taxonomy of memory in LLMs. Our framework characterizes memory along three orthogonal axes: representation (implicit versus explicit), update dynamics (offline versus online), and persistence (short-term versus long-term). We further formalize the granular mechanisms dictating memory writing, routing, state transitions, and consolidation. This unified perspective elucidates the conceptual boundaries between computation-coupled and independently addressable memory, effectively bridging disparate architectural paradigms. Additionally, we critically analyze hybrid memory architectures, system-level efficiency trade-offs, and multi-dimensional evaluation methodologies. By consolidating these scattered advancements into a cohesive framework, this survey charts the trajectory of memory-centric LLM design and provides a principled foundation for future innovations in scalable and adaptive language modeling.
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。