"This repository is the code for the paper "Exploring Large Language Models for Communication Games: An Empirical Study on Werewolf". In this paper, we explore the problem of how to engage large language models (LLMs) in communication games, and in response, propose a tuning-free framework. Our approach keeps LLMs frozen, and relies on the retrieval and reflection on past communications and experiences for improvement. An empirical study on the representative and widely-studied communication game, "Werewolf", demonstrates that our framework can effectively play Werewolf game without tuning the parameters of the LLMs. More importantly, strategic behaviors begin to emerge in our experiments, suggesting that it will be a fruitful journey to engage LLMs in communication games and associated domains."<p>arXiv paper: <a href="https://arxiv.org/abs/2309.04658" rel="nofollow">https://arxiv.org/abs/2309.04658</a>