对话时刻：大语言模型代理在“狼人杀”游戏中的异步群体沟通应用

摘要

大型语言模型（LLMs）主要应用于同步通信场景，即人类用户与模型交替进行对话。然而，许多现实世界的情境本质上是异步的。例如，在群聊、在线团队会议或社交游戏中，并不存在固有的轮次概念；因此，决定何时发言成为参与者决策过程中的关键环节。在本研究中，我们开发了一种自适应异步LLM代理，该代理不仅确定发言内容，还决定发言时机。为了评估我们的代理，我们收集了一套独特的在线“狼人杀”游戏数据集，其中包括人类参与者以及我们的异步代理。总体而言，我们的代理在游戏表现及与人类玩家融合的能力上均与人类玩家相当。分析显示，代理在决定发言时机上的行为与人类模式高度相似，尽管在消息内容上存在差异。我们公开了所有数据和代码，以支持和鼓励进一步研究，推动LLM代理之间实现更为真实的异步通信。本工作为将LLMs整合到现实的人类群体环境中铺平了道路，从协助团队讨论到需要在复杂社交动态中导航的教育及职业环境，均具有广泛的应用前景。

English

LLMs are used predominantly in synchronous communication, where a human user and a model communicate in alternating turns. In contrast, many real-world settings are inherently asynchronous. For example, in group chats, online team meetings, or social games, there is no inherent notion of turns; therefore, the decision of when to speak forms a crucial part of the participant's decision making. In this work, we develop an adaptive asynchronous LLM-agent which, in addition to determining what to say, also decides when to say it. To evaluate our agent, we collect a unique dataset of online Mafia games, including both human participants, as well as our asynchronous agent. Overall, our agent performs on par with human players, both in game performance, as well as in its ability to blend in with the other human players. Our analysis shows that the agent's behavior in deciding when to speak closely mirrors human patterns, although differences emerge in message content. We release all our data and code to support and encourage further research for more realistic asynchronous communication between LLM agents. This work paves the way for integration of LLMs into realistic human group settings, from assistance in team discussions to educational and professional environments where complex social dynamics must be navigated.

对话时刻：大语言模型代理在“狼人杀”游戏中的异步群体沟通应用

Time to Talk: LLM Agents for Asynchronous Group Communication in Mafia Games

摘要

Support