Saved in:
Bibliographic Details
Main Authors: Jiang, Zexun, Shi, Yafang, Li, Maoxu, Xiao, Hongjiang, Qin, Yunxiao, Wei, Qinglan, Wang, Ye, Zhang, Yuan
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2412.19498
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912170359390208
author Jiang, Zexun
Shi, Yafang
Li, Maoxu
Xiao, Hongjiang
Qin, Yunxiao
Wei, Qinglan
Wang, Ye
Zhang, Yuan
author_facet Jiang, Zexun
Shi, Yafang
Li, Maoxu
Xiao, Hongjiang
Qin, Yunxiao
Wei, Qinglan
Wang, Ye
Zhang, Yuan
contents In this paper, we introduce a multi-agent simulation framework Casevo (Cognitive Agents and Social Evolution Simulator), that integrates large language models (LLMs) to simulate complex social phenomena and decision-making processes. Casevo is designed as a discrete-event simulator driven by agents with features such as Chain of Thoughts (CoT), Retrieval-Augmented Generation (RAG), and Customizable Memory Mechanism. Casevo enables dynamic social modeling, which can support various scenarios such as social network analysis, public opinion dynamics, and behavior prediction in complex social systems. To demonstrate the effectiveness of Casevo, we utilize one of the U.S. 2020 midterm election TV debates as a simulation example. Our results show that Casevo facilitates more realistic and flexible agent interactions, improving the quality of dynamic social phenomena simulation. This work contributes to the field by providing a robust system for studying large-scale, high-fidelity social behaviors with advanced LLM-driven agents, expanding the capabilities of traditional agent-based modeling (ABM). The open-source code repository address of casevo is https://github.com/rgCASS/casevo.
format Preprint
id arxiv_https___arxiv_org_abs_2412_19498
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Casevo: A Cognitive Agents and Social Evolution Simulator
Jiang, Zexun
Shi, Yafang
Li, Maoxu
Xiao, Hongjiang
Qin, Yunxiao
Wei, Qinglan
Wang, Ye
Zhang, Yuan
Social and Information Networks
In this paper, we introduce a multi-agent simulation framework Casevo (Cognitive Agents and Social Evolution Simulator), that integrates large language models (LLMs) to simulate complex social phenomena and decision-making processes. Casevo is designed as a discrete-event simulator driven by agents with features such as Chain of Thoughts (CoT), Retrieval-Augmented Generation (RAG), and Customizable Memory Mechanism. Casevo enables dynamic social modeling, which can support various scenarios such as social network analysis, public opinion dynamics, and behavior prediction in complex social systems. To demonstrate the effectiveness of Casevo, we utilize one of the U.S. 2020 midterm election TV debates as a simulation example. Our results show that Casevo facilitates more realistic and flexible agent interactions, improving the quality of dynamic social phenomena simulation. This work contributes to the field by providing a robust system for studying large-scale, high-fidelity social behaviors with advanced LLM-driven agents, expanding the capabilities of traditional agent-based modeling (ABM). The open-source code repository address of casevo is https://github.com/rgCASS/casevo.
title Casevo: A Cognitive Agents and Social Evolution Simulator
topic Social and Information Networks
url https://arxiv.org/abs/2412.19498