Large Language Models (LLMs) have made extraordinary progress in the field of Artificial Intelligence and have demonstrated remarkable capabilities across a large variety of tasks and domains. However, as we venture closer to creating Artificial General Intelligence (AGI) systems, we recognize the need to supplement LLMs with long-term memory to overcome the context window limitation and more importantly, to create a foundation for sustained reasoning, cumulative learning and long-term user interaction. In this paper we propose RecallM, a novel architecture for providing LLMs with an adaptable and updatable long-term memory mechanism. Unlike previous methods, the RecallM architecture is particularly effective at belief updating and maintaining a temporal understanding of the knowledge provided to it. We demonstrate through various experiments the effectiveness of this architecture. Furthermore, through our own temporal understanding and belief updating experiments, we show that RecallM is four times more effective than using a vector database for updating knowledge previously stored in long-term memory. We also demonstrate that RecallM shows competitive performance on general question-answering and in-context learning tasks.

翻译：大语言模型在人工智能领域取得了非凡进展，并在多种任务和领域中展现出卓越能力。然而，随着我们逐步接近创造通用人工智能系统，我们意识到需要为大语言模型补充长期记忆，以克服上下文窗口限制，更重要的是为持续推理、累积学习和长期用户交互奠定基础。本文提出RecallM——一种为大语言模型提供可自适应、可更新长期记忆机制的新型架构。与以往方法不同，RecallM架构在信念更新及维护所提供知识的时间理解方面尤为有效。通过多项实验，我们验证了该架构的有效性。此外，基于自主设计的时间理解与信念更新实验，我们发现RecallM在更新已存储于长期记忆中的知识时，其效率比使用向量数据库高出四倍。我们还证明RecallM在通用问答与上下文学习任务中展现出具有竞争力的性能。