Communication is a fundamental aspect of human society, facilitating the exchange of information and beliefs among people. Despite the advancements in large language models (LLMs), recent agents built with these often neglect the control over discussion tactics, which are essential in communication scenarios and games. As a variant of the famous communication game Werewolf, One Night Ultimate Werewolf (ONUW) requires players to develop strategic discussion policies due to the potential role changes that increase the uncertainty and complexity of the game. In this work, we first present the existence of the Perfect Bayesian Equilibria (PBEs) in two scenarios of the ONUW game: one with discussion and one without. The results showcase that the discussion greatly changes players' utilities by affecting their beliefs, emphasizing the significance of discussion tactics. Based on the insights obtained from the analyses, we propose an RL-instructed language agent framework, where a discussion policy trained by reinforcement learning (RL) is employed to determine appropriate discussion tactics to adopt. Our experimental results on several ONUW game settings demonstrate the effectiveness and generalizability of our proposed framework.

翻译：交流是人类社会的基本要素，促进着人与人之间的信息与信念交换。尽管大语言模型（LLM）取得了显著进展，但基于这些模型构建的智能体往往忽视了对讨论策略的控制，而这在交流场景与游戏中至关重要。作为著名交流游戏“狼人杀”的变体，《一夜终极狼人杀》（ONUW）因潜在的角色变动增加了游戏的不确定性与复杂性，要求玩家制定策略性的讨论策略。在本研究中，我们首先证明了在ONUW游戏的两种场景（有讨论与无讨论）中完美贝叶斯均衡（PBE）的存在性。结果表明，讨论通过影响玩家的信念显著改变了其收益，凸显了讨论策略的重要性。基于分析所得启示，我们提出了一种RL指导的语言智能体框架，其中采用通过强化学习（RL）训练的讨论策略来决定应采用的合适讨论战术。我们在多个ONUW游戏设定中的实验结果验证了所提框架的有效性与泛化能力。