The ideal long-term memory mechanism for Large Language Model (LLM) based chatbots, would lay the foundation for continual learning, complex reasoning and allow sequential and temporal dependencies to be learnt. Creating this type of memory mechanism is an extremely challenging problem. In this paper we explore different methods of achieving the effect of long-term memory. We propose a new architecture focused on creating adaptable and updatable long-term memory for AGI systems. We demonstrate through various experiments the benefits of the RecallM architecture, particularly the improved temporal understanding it provides.

翻译：基于大语言模型的聊天机器人理想长期记忆机制，应为持续学习、复杂推理奠定基础，并支持学习序列依赖与时间依赖。构建此类记忆机制是一项极具挑战性的问题。本文探索了实现长期记忆效果的不同方法，提出了一种聚焦于为通用人工智能系统创建可适应、可更新的长期记忆的新型架构。通过多项实验，我们论证了RecallM架构的优势，特别是在提升时间理解能力方面的显著效果。