Saved in:
Bibliographic Details
Main Authors: Lan, Yihuai, Hu, Zhiqiang, Wang, Lei, Wang, Yang, Ye, Deheng, Zhao, Peilin, Lim, Ee-Peng, Xiong, Hui, Wang, Hao
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2310.14985
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910646981885952
author Lan, Yihuai
Hu, Zhiqiang
Wang, Lei
Wang, Yang
Ye, Deheng
Zhao, Peilin
Lim, Ee-Peng
Xiong, Hui
Wang, Hao
author_facet Lan, Yihuai
Hu, Zhiqiang
Wang, Lei
Wang, Yang
Ye, Deheng
Zhao, Peilin
Lim, Ee-Peng
Xiong, Hui
Wang, Hao
contents This paper explores the open research problem of understanding the social behaviors of LLM-based agents. Using Avalon as a testbed, we employ system prompts to guide LLM agents in gameplay. While previous studies have touched on gameplay with LLM agents, research on their social behaviors is lacking. We propose a novel framework, tailored for Avalon, features a multi-agent system facilitating efficient communication and interaction. We evaluate its performance based on game success and analyze LLM agents' social behaviors. Results affirm the framework's effectiveness in creating adaptive agents and suggest LLM-based agents' potential in navigating dynamic social interactions. By examining collaboration and confrontation behaviors, we offer insights into this field's research and applications. Our code is publicly available at https://github.com/3DAgentWorld/LLM-Game-Agent.
format Preprint
id arxiv_https___arxiv_org_abs_2310_14985
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle LLM-Based Agent Society Investigation: Collaboration and Confrontation in Avalon Gameplay
Lan, Yihuai
Hu, Zhiqiang
Wang, Lei
Wang, Yang
Ye, Deheng
Zhao, Peilin
Lim, Ee-Peng
Xiong, Hui
Wang, Hao
Computation and Language
This paper explores the open research problem of understanding the social behaviors of LLM-based agents. Using Avalon as a testbed, we employ system prompts to guide LLM agents in gameplay. While previous studies have touched on gameplay with LLM agents, research on their social behaviors is lacking. We propose a novel framework, tailored for Avalon, features a multi-agent system facilitating efficient communication and interaction. We evaluate its performance based on game success and analyze LLM agents' social behaviors. Results affirm the framework's effectiveness in creating adaptive agents and suggest LLM-based agents' potential in navigating dynamic social interactions. By examining collaboration and confrontation behaviors, we offer insights into this field's research and applications. Our code is publicly available at https://github.com/3DAgentWorld/LLM-Game-Agent.
title LLM-Based Agent Society Investigation: Collaboration and Confrontation in Avalon Gameplay
topic Computation and Language
url https://arxiv.org/abs/2310.14985