Exploring Large Language Models for Communication Games: An Empirical Study on Werewolf
By Yuzhuang Xu, Shuo Wang, Peng Li, Fuwen Luo, Xiaolong Wang, Weidong Liu, Yang Liu. arXiv.org, 2023
303 citations recorded by the source corpus.
Communication games, which we refer to as incomplete information games that heavily depend on natural language communication, hold significant research value in fields such as economics, social science, and artificial intelligence. In this work, 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.
Subfields: Artificial Intelligence, General Social Sciences
View Paper: https://www.semanticscholar.org/paper/24d52678c887331b9da0368e8a2f58bec07f7203
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Nitesh V. Chawla
- Francisco Herrera
- Gianluca Bontempi
- Andrea Dal Pozzolo
- Charu C. Aggarwal
- Alberto Fernández
- Vasile Palade
- Taghi M. Khoshgoftaar
Citations in the corpus
- AppAgent: Multimodal Agents as Smartphone Users (2023, unknown): “In our approach, the agent learns from human demonstrations or its own exploration, aligning with the objective of PbD by enabling task learning through examples, thus simplifying task automation.”
- Large Language Model based Multi-Agents: A Survey of Progress and Challenges (2024, methodology): “This technology enables the development of controlled, scalable, and dynamic settings that closely mimic human interactions, making it ideal for testing a range of game theory hypotheses [Mao et al. , 2023; Xu et al. , 2023b; Gong et al. , 2023].”
- The rise and potential of large language model based agents: a survey (2025, unknown): “Recently, LLM-based agents have exhibited spontaneous social behaviors in an environment [404].”