Exploring Large Language Models for Communication Games: An Empirical Study on Werewolf
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.
Code (1)
Tasks
RetrievalSimilar Papers 제목 키워드 기반
Inductive Bias and Language Expressivity in Emergent Communication
Referential games and reconstruction games are the most common game types for studying emergent languages. We investigate how the type of the language game affects the emergent language in terms of: i) language compositi…
Inductive BiasIncorporating Pragmatic Reasoning Communication into Emergent Language
Emergentism and pragmatics are two research fields that study the dynamics of linguistic communication along substantially different timescales and intelligence levels. From the perspective of multi-agent reinforcement l…
Multi-agent Reinforcement LearningReinforcement Learning (RL)StarcraftStarcraft IITowards Effective and Interpretable Human-Agent Collaboration in MOBA Games: A Communication Perspective
MOBA games, e.g., Dota2 and Honor of Kings, have been actively used as the testbed for the recent AI research on games, and various AI systems have been developed at the human level so far. However, these AI systems main…
Human Agent CollaborationComputational Results for Extensive-Form Adversarial Team Games
We provide, to the best of our knowledge, the first computational study of extensive-form adversarial team games. These games are sequential, zero-sum games in which a team of players, sharing the same utility function, …
FormCoMet: Metaphor-Driven Covert Communication for Multi-Agent Language Games
Metaphors are a crucial way for humans to express complex or subtle ideas by comparing one concept to another, often from a different domain. However, many large language models (LLMs) struggle to interpret and apply met…