This paper aims to investigate the open research problem of uncovering the social behaviors of LLM-based agents. To achieve this goal, we adopt Avalon, a representative communication game, as the environment and use system prompts to guide LLM agents to play the game. While previous studies have conducted preliminary investigations into gameplay with LLM agents, there lacks research on their social behaviors. In this paper, we present a novel framework designed to seamlessly adapt to Avalon gameplay. The core of our proposed framework is a multi-agent system that enables efficient communication and interaction among agents. We evaluate the performance of our framework based on metrics from two perspectives: winning the game and analyzing the social behaviors of LLM agents. Our results demonstrate the effectiveness of our framework in generating adaptive and intelligent agents and highlight the potential of LLM-based agents in addressing the challenges associated with dynamic social environment interaction. By analyzing the social behaviors of LLM agents from the aspects of both collaboration and confrontation, we provide insights into the research and applications of this domain.

翻译：本文旨在探究基于大语言模型（LLM）的智能体社会行为这一开放性研究问题。为实现该目标，我们选取具有代表性的交流博弈游戏阿瓦隆作为实验环境，通过系统提示指导LLM智能体进行游戏。尽管已有研究初步探讨了LLM智能体在游戏中的表现，但针对其社会行为的系统性研究仍属空白。本文提出了一种可无缝适配阿瓦隆游戏的全新框架，其核心是构建支持智能体间高效通信与交互的多智能体系统。我们从游戏获胜与LLM智能体社会行为分析两个维度评估框架性能。实验结果表明，该框架能够生成具备适应性与智能性的智能体，并揭示了基于LLM的智能体在应对动态社会环境交互挑战中的潜力。通过从合作与对抗双重视角分析LLM智能体的社会行为，本文为该领域的研究与应用提供了重要洞见。