Related papers: RLupus: Cooperation through emergent communication…
Social deduction games like Werewolf combine language, reasoning, and strategy, providing a testbed for studying natural language and social intelligence. However, most studies reduce the game to LLM-based self-play, yielding templated…
Large Language Models (LLMs) have advanced the capability of game agents in social deduction games (SDGs). These games rely heavily on conversation-driven interactions and require agents to infer, make decisions, and express based on such…
The growing popularity of social deduction games has created an increasing need for intelligent frameworks where humans can collaborate with AI agents, particularly in post-pandemic contexts with heightened psychological and social…
The Werewolf game is a social deduction game based on free natural language communication, in which players try to deceive others in order to survive. An important feature of this game is that a large portion of the conversations are false…
Recent advancements in natural language processing, particularly with large language models (LLMs) like GPT-4, have significantly enhanced dialogue systems, enabling them to generate more natural and fluent conversations. Despite these…
This paper introduces Werewolf Arena, a novel framework for evaluating large language models (LLMs) through the lens of the classic social deduction game, Werewolf. In Werewolf Arena, LLMs compete against each other, navigating the game's…
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…
Persuasion modeling is a key building block for conversational agents. Existing works in this direction are limited to analyzing textual dialogue corpus. We argue that visual signals also play an important role in understanding human…
In Social Deduction Games (SDGs) such as Avalon, Mafia, and Werewolf, players conceal their identities and deliberately mislead others, making hidden-role inference a central and demanding task. Accurate role identification, which forms the…
Agents built with large language models (LLMs) have shown great potential across a wide range of domains. However, in complex decision-making tasks, pure LLM-based agents tend to exhibit intrinsic bias in their choice of actions, which is…
Werewolf is a popular party game throughout the world, and research on its significance has progressed in recent years. The Werewolf game is based on conversation, and in order to win, participants must use all of their cognitive abilities.…
Large language model (LLM) agents have shown remarkable progress in social deduction games (SDGs). However, existing approaches primarily focus on information processing and strategy selection, overlooking the significance of persuasive…
The emergence and maintenance of cooperation within sizable groups of unrelated humans offer many challenges for our understanding. We propose that the humans' capacity of communication, such as how many and how far away the fellows can…
We study the evolution of cooperation in the evolutionary spatial prisoner's dilemma game (PDG) and snowdrift game (SG), within which a fraction $\alpha$ of the payoffs of each player gained from direct game interactions is shared equally…
Whether or not to change strategy depends not only on the personal success of each individual, but also on the success of others. Using this as motivation, we study the evolution of cooperation in games that describe social dilemmas, where…
We study the evolution of cooperation in structured populations within popular models of social dilemmas, whereby simple coevolutionary rules are introduced that may enhance players abilities to enforce their strategy on the opponent.…
Communicating in natural language is a powerful tool in multi-agent settings, as it enables independent agents to share information in partially observable settings and allows zero-shot coordination with humans. However, most prior works…
The Werewolf Game is a communication game where players' reasoning and discussion skills are essential. In this study, we present a Werewolf AI agent developed for the AIWolfDial 2024 shared task, co-hosted with the 17th INLG. In recent…
The evolutionary Prisoner's Dilemma Game (PDG) and the Snowdrift Game (SG) with preferential learning mechanism are studied in the Barab\'asi-Albert network. Simulation results demonstrate that the preferential learning of individuals…
The construction of reciprocal relationships requires cooperative interactions during the initial meetings. However, cooperative behavior with strangers is risky because the strangers may be exploiters. In this study, we show that people…