A Social Group Chatbot System by Multiple Topics Tracking and Atkinson-Shiffrin Memory Model Using AI Agents Collaboration

作     者：Zhang, Guoshuai Wu, Jiaji Jeon, Gwanggil Wang, Penghui 

作者机构：Xidian Univ Sch Elect Engn Xian Peoples R China Incheon Natl Univ Dept Embedded Syst Engn Seoul South Korea 

出 版 物：《EXPERT SYSTEMS》 (Expert Syst)

年 卷 期：2025年第42卷第2期

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：Postdoctoral Fellowship Program of CPSF China Postdoctoral Science Foundation [2024M752529] National Natural Science Foundation of China GZC20232057 

主　　题：agents collaboration large language model memory model social group chatbot topics tracking 

摘      要：The widespread use of Internet has accelerated the explosive growth of data, which in turn leads to information overload and information confusion. This makes it difficult for us to communicate effectively in social groups, thereby intensifying the demands for emotional companionship. Therefore, we propose a novel social group chatting framework based on Large Language Model (LLM) powered multiple autonomous agents collaboration in this article. Specifically, BERTopic is used to extract topics from history chatting content for each social group everyday, and then multiple topics tracking is realised through multi-level association by adaptive time sliding-window mechanism and optimal matching. Furthermore, we use topic tracking architecture and prompts to design and implement an AI Chatbot system with different characters that can conduct natural language conversations with users in online social group. LLM, as the controller and coordinator of the whole AI Chatbot for sub-tasks, allows different AI Agents to autonomously decide whether to participate in current topic, how to generate response, and whether to propose a new topic. Each AI Agent has their own multi-store memory system based on the Atkinson-Shiffrin model. Finally, we construct a verification environment based on online game that is consistent with real society. Subjective and objective evaluation methods were deployed to perform qualitative and quantitative analyses to demonstrate the performance of our AI Chatbot system.