In this study, we explore the application of Large Language Models (LLMs) in "Jubensha" (Chinese murder mystery role-playing games), a novel area in AI-driven gaming. We introduce the first Chinese dataset specifically for Jubensha, including character scripts and game rules, to foster AI agent development in this complex narrative environment. Our work also presents a unique multi-agent interaction framework using LLMs, allowing AI agents to autonomously engage in the game, enhancing the dynamics of Jubensha gameplay. To evaluate these AI agents, we developed specialized methods targeting their mastery of case information and reasoning skills. Furthermore, we incorporated the latest advancements in in-context learning to improve the agents' performance in critical aspects like information gathering, murderer detection, and logical reasoning. The experimental results validate the effectiveness of our proposed methods. This work aims to offer a fresh perspective on understanding LLM capabilities and establish a new benchmark for evaluating large language model-based agents to researchers in the field.

翻译：本研究探索了大语言模型在“剧本杀”（中国谋杀悬疑角色扮演游戏）中的应用，这是人工智能驱动游戏中的一个新兴领域。我们首次引入了专门针对剧本杀的中文数据集，包括角色剧本和游戏规则，以促进这一复杂叙事环境中AI智能体的开发。本文还提出了一种基于大语言模型的独特多智能体交互框架，使AI智能体能够自主参与游戏，增强剧本杀玩法的动态性。为评估这些AI智能体，我们开发了专门的方法，聚焦其对案件信息的掌握程度和推理能力。此外，我们融入了上下文学习的最新进展，以提升智能体在信息收集、凶手识别和逻辑推理等关键方面的表现。实验结果验证了我们所提方法的有效性。本研究旨在为大语言模型的能力理解提供新视角，并为本领域研究人员建立基于大语言模型的智能体评估新基准。