The 3rd International Workshop of AI Werewolf and Dialog System (AIWolfDial2025)

Collocated with INLG 2025 conference, September 30, 2025, Hanoi, Vietnam

Workshop website: https://aiwolfdial.github.io/aiwolf-nlp/en/

Workshop aims

Recent achievements of generation models, e.g. ChatGPT, are gathering greater attentions. However, such a huge language model would not be sufficiently able to handle coherent responses, longer contexts, common grounds, and logics.

The AIWolfDial 2025 contest is held as a part of this AIWolfDial2025 workshop. This is an international open contest for automatic players of the conversation game "Mafia", requires players not just to communicate but to infer, persuade, deceive other players via coherent logical conversations, while having the role-playing non-task-oriented chats as well. We believe that this contest reveals current issues in the recent huge language models, showing directions of next breakthrough in the NLP area.

From the viewpoint of Game AI area, players must hide information, in contrast to perfect information games such as chess or Reversi. Each player acquires secret information from other players' conversations and behavior and acts by hiding information to accomplish their objectives. Players are required persuasion for earning confidence, and speculation for detecting fabrications.

We call for papers which include following topics but not limited to:

  • AI werewolf agents for natural language and/or protocols
  • Natural language processing and LLMs for games
  • Corpora, resources, analysis on conversation games
  • Natural language processing for human relationships
  • Natural language processing for logic and strategy
  • Imperfect information game and natural language
  • Deceiving and persuasion by automatic agents
  • Evaluation of dialog systems using games

Important dates

Workshop papers

  • September 10, 2025: Paper Submission Deadline　← New! deadline extended
  • September 24, 2025: Notification of Acceptance
  • October 1, 2025: Camera-ready Submission Deadline　← New! deadline moved

INLG 2025 Conference Period

  • October 29 - November 2, 2025 (in Hanoi)
  • October 30, 2025: AIWolfDial 2025 Workshop in Hanoi/online (Paper Presentations and Competition Results)

Note: Please observe our workshop website for updates.

Submission

We call for short papers and long papers as same as the INLG main conference, both for shared task papers and papers in general. Please use the ACL format as specified in the INLG conference webpage.

Submission site: https://softconf.com/p/AIWolfDial2025/

Shared task

Recent achievements of generation models, e.g. ChatGPT, are gathering greater attentions. However, there is still room to investigate LLMs could sufficiently able to handle coherent responses, longer contexts, common grounds, and logics. Werewolf is a social, hidden identity game that requires debate between players and coalition building. The goal of our AIWerewolf contest is to build an AI agent that is able to play this game against other AI. We will hold 5-players and 13-players tracks.

Shared task registration form: https://forms.gle/WuZdfjFAvLV98NU49

For detailed information, please refer to our call for participation sent separately, which is shown in our workshop website.

Committee

Contact: E-mail to aiwolf at kanolab.net (replace at by @)

Organizers

Organizers and Program Commitee:

  • Yoshinobu Kano, Shizuoka University, Japan
  • Claus Aranha, Tsukuba University
  • Takashi Otsuki, Yamagata University, Japan
  • Fujio Toriumi, The University of Tokyo, Japan
  • Hirotaka Osawa, Keio University, Japan
  • Daisuke Katagami, Tokyo Polytechnic University, Japan
  • Michimasa Inaba, The University of Electro-Communications, Japan
  • Kei Harada, The University of Electro-Communications, Japan
  • Takeshi Ito, The University of Electro-Communications, Japan

Local Organizers:

  • Neo Watanabe, Shizuoka University, Japan
  • Yuto Sahashi, Shizuoka University, Japan
  • Yuya Harada, Shizuoka University, Japan