Jiafeng Liang, Hao Li, Chang Li, Jiaqi Zhou, Shixin Jiang, Zekun Wang, Changkai Ji, Zhihao Zhu, Runxuan Liu, Tao Ren, Jinlan Fu, See-Kiong Ng, Xia Liang, Ming Liu, Bing Qin
This paper bridges cognitive neuroscience and AI by synthesizing interdisciplinary knowledge on memory systems for autonomous agents, offering insights into memory mechanisms, taxonomy, and security, and proposing future research directions.
This research paper explores how autonomous agents, like AI systems, can benefit from the study of human memory systems as understood in cognitive neuroscience. By examining and comparing how memory works in both humans and AI, the authors aim to improve how AI systems store and use information. They also discuss the security of these memory systems and suggest future areas of research, such as integrating different types of memories and improving skill learning in AI. The goal is to create AI systems that can better mimic human memory processes to perform complex tasks more effectively.
