Large language models (LLMs) have achieved impressive linguistic capabilities. However, a key limitation persists in their lack of human-like memory faculties. LLMs exhibit constrained memory retention across sequential interactions, hindering complex reasoning. This paper explores the potential of applying cognitive psychology's working memory frameworks, to enhance LLM architecture. The limitations of traditional LLM memory designs are analyzed, including their isolation of distinct dialog episodes and lack of persistent memory links. To address this, an innovative model is proposed incorporating a centralized Working Memory Hub and Episodic Buffer access to retain memories across episodes. This architecture aims to provide greater continuity for nuanced contextual reasoning during intricate tasks and collaborative scenarios. While promising, further research is required into optimizing episodic memory encoding, storage, prioritization, retrieval, and security. Overall, this paper provides a strategic blueprint for developing LLM agents with more sophisticated, human-like memory capabilities, highlighting memory mechanisms as a vital frontier in artificial general intelligence.

翻译：大型语言模型（LLMs）已展现出卓越的语言能力。然而，其关键局限在于缺乏类人的记忆功能。LLMs在连续交互中表现出受限的记忆保持能力，阻碍了复杂推理。本文探讨了应用认知心理学中的工作记忆框架来增强LLM架构的潜力。文章分析了传统LLM记忆设计的局限性，包括其对不同对话片段的孤立处理以及缺乏持久记忆链接。为解决这一问题，本文提出了一种创新模型，该模型包含一个集中的工作记忆中枢和情景缓冲器访问机制，以跨片段保留记忆。该架构旨在为复杂任务和协作场景中的细致上下文推理提供更强的连续性。尽管前景广阔，但在情景记忆的编码、存储、优先级排序、检索和安全性优化方面仍需进一步研究。总体而言，本文为开发具有更复杂、更类人记忆能力的LLM智能体提供了战略蓝图，并强调了记忆机制作为通用人工智能发展的一个关键前沿领域。