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

TL;DR

This study investigates the social behaviors of LLM-based agents in Avalon gameplay, introducing a novel multi-agent framework to analyze their collaboration and confrontation dynamics, demonstrating effective adaptive social interactions.

Contribution

The paper presents a new framework tailored for Avalon that enables LLM agents to exhibit and analyze social behaviors like collaboration and confrontation.

Findings

Framework effectively facilitates adaptive social behaviors.

LLM agents demonstrate nuanced collaboration and confrontation.

Potential for LLM agents to navigate complex social interactions.

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. Our code is publicly available at https://github.com/3DAgentWorld/LLM-Game-Agent.