基于LLM的智能体社会调查:Avalon游戏中的协作与对抗
LLM-Based Agent Society Investigation: Collaboration and Confrontation in Avalon Gameplay
AI总结:
本文提出专为Avalon游戏设计的多智能体框架,通过系统提示引导LLM智能体,评估其游戏表现并分析协作与对抗等社会行为,证实了框架创建自适应智能体的有效性及LLM在动态社交中的潜力。
摘要:
本文探讨了理解基于LLM的智能体社会行为的开放研究问题。以Avalon为测试平台,我们使用系统提示来引导LLM智能体进行游戏。尽管先前的研究涉及过LLM智能体游戏,但对其社会行为的研究仍然缺乏。我们提出了一个专为Avalon设计的新颖框架,该框架具有一个促进高效通信和交互的多智能体系统。我们基于游戏成功与否评估其性能,并分析LLM智能体的社会行为。结果证实了该框架在创建自适应智能体方面的有效性,并表明基于LLM的智能体在驾驭动态社会互动方面的潜力。通过考察协作和对抗行为,我们提供了对该领域研究和应用的见解。我们的代码在https://github.com/3DAgentWorld/LLM-Game-Agent上公开可用。
英文摘要:
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.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。