LLM-Based Agent Society Investigation: Collaboration and Confrontation in Avalon Gameplay

Yihuai Lan, Zhiqiang Hu, Lei Wang, Yang Wang, Deheng Ye, Peilin Zhao, Ee-Peng Lim, Hui Xiong, Hao Wang


Abstract
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.
Anthology ID:
2024.emnlp-main.7
Volume:
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
128–145
Language:
URL:
https://aclanthology.org/2024.emnlp-main.7
DOI:
10.18653/v1/2024.emnlp-main.7
Bibkey:
Cite (ACL):
Yihuai Lan, Zhiqiang Hu, Lei Wang, Yang Wang, Deheng Ye, Peilin Zhao, Ee-Peng Lim, Hui Xiong, and Hao Wang. 2024. LLM-Based Agent Society Investigation: Collaboration and Confrontation in Avalon Gameplay. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 128–145, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
LLM-Based Agent Society Investigation: Collaboration and Confrontation in Avalon Gameplay (Lan et al., EMNLP 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.emnlp-main.7.pdf