Workshop Proceedings (peer reviewed)
Proceedings of the AIWolfDial workshops co-located with INLG. Each volume contains the contest summary paper and papers by participating teams and related research.
AIWolfDial 2025 (INLG 2025, Hanoi)
- AIWolfDial 2025: Summary of Natural Language Division of 7th International AIWolf Contest. Yoshinobu Kano, Neo Watanabe, Yuya Harada, Yuto Sahashi, Claus Aranha, Daisuke Katagami, Kei Harada, Michimasa Inaba, Takeshi Ito, Hirotaka Osawa, Takashi Otsuki, Fujio Toriumi.
- Towards a Strategic Werewolf AI Based on Expert Strategies in Five-Player Werewolf. Takuma Okada, Takeshi Ito.
- Intent-driven AIWolf Agents with Hierarchical BDI Model and Personality. Yuya Harada, Yoshinobu Kano.
- Influence of Utterance Impressions on Decision-Making in LLM-to-LLM Discussions. Neo Watanabe, Yoshinobu Kano.
AIWolfDial 2024 (INLG 2024, Tokyo)
- AIWolfDial 2024: Summary of Natural Language Division of 6th International AIWolf Contest. Yoshinobu Kano, Yuto Sahashi, Neo Watanabe, Kaito Kagaminuma, Claus Aranha, Daisuke Katagami, Kei Harada, Michimasa Inaba, Takeshi Ito, Hirotaka Osawa, Takashi Otsuki, Fujio Toriumi.
- Text Generation Indistinguishable from Target Person by Prompting Few Examples Using LLM. Yuka Tsubota, Yoshinobu Kano.
- Werewolf Game Agent by Generative AI Incorporating Logical Information Between Players. Neo Watanabe, Yoshinobu Kano.
- Enhancing Dialogue Generation in Werewolf Game Through Situation Analysis and Persuasion Strategies. Zhiyang Qi, Michimasa Inaba.
- Verification of Reasoning Ability using BDI Logic and Large Language Model in AIWolf. Hiraku Gondo, Hiroki Sakaji, Itsuki Noda.
- Enhancing Consistency of Werewolf AI through Dialogue Summarization and Persona Information. Yoshiki Tanaka, Takumasa Kaneko, Hiroki Onozeki, Natsumi Ezure, Ryuichi Uehara, Zhiyang Qi, Tomoya Higuchi, Ryutaro Asahara, Michimasa Inaba.
- An Implementation of Werewolf Agent That does not Truly Trust LLMs. Takehiro Sato, Shintaro Ozaki, Daisaku Yokoyama.
INLG 2023 Generation Challenges (Prague)
- AIWolfDial 2023: Summary of Natural Language Division of 5th International AIWolf Contest. Yoshinobu Kano, Neo Watanabe, Kaito Kagaminuma, Claus Aranha, Jaewon Lee, Benedek Hauer, Hisaichi Shibata, Soichiro Miki, Yuta Nakamura, Takuya Okubo, Soga Shigemura, Rei Ito, Kazuki Takashima, Tomoki Fukuda, Masahiro Wakutani, Tomoya Hatanaka, Mami Uchida, Mikio Abe, Akihiro Mikami, Takashi Otsuki, Zhiyang Qi, Kei Harada, Michimasa Inaba, Daisuke Katagami, Hirotaka Osawa, Fujio Toriumi.
Publications by the Organizers
Overview papers of the contests and related publications by the organizing members.
Overview
Yoshinobu Kano, Daisuke Katagami, Claus Aranha, Takeshi Ito, Michimasa Inaba, Hirotaka Osawa, Takashi Otsuki, Fujio Toriumi, Kei Harada. 人狼知能コンテスト2025春季国内大会自然言語部門 [Natural Language Division of the AIWolf Contest 2025 Spring Domestic Tournament]. The 39th Annual Conference of the Japanese Society for Artificial Intelligence (JSAI 2025). Osaka International Convention Center (Grand Cube Osaka). 2025/5/30
Yoshinobu Kano, Reo Watanabe, Yuto Sahashi, Ami Sakane, Fujio Toriumi, Michimasa Inaba, Hirotaka Osawa, Daisuke Katagami, Takashi Otsuki, Claus Aranha, Kei Harada, Takeshi Ito. 人狼知能コンテスト2024冬季国内大会自然言語部門の概要 [Overview of the Natural Language Division of the AIWolf Contest 2024 Winter Domestic Tournament]. The 31st Annual Meeting of the Association for Natural Language Processing (NLP2025). Dejima Messe Nagasaki. 2025/3/12
Yoshinobu Kano, Fujio Toriumi, Michimasa Inaba, Hirotaka Osawa, Daisuke Katagami, Takashi Otsuki, Claus Aranha, Kei Harada. KS-8「人狼知能コンテスト2024国内大会自然言語部門」[KS-8: Natural Language Division of the AIWolf Contest 2024 Domestic Tournament]. Special Feature: “38th Annual Conference of the Japanese Society for Artificial Intelligence (JSAI 2024) [Organized Session Summary, KS1–20]”. Journal of the Japanese Society for Artificial Intelligence, Vol. 39, No. 6, p. 864. 2024/11/1
Yoshinobu Kano, Yuto Sahashi, Neo Watanabe, Kaito Kagaminuma, Claus Aranha, Daisuke Katagami, Kei Harada, Michimasa Inaba, Takeshi Ito, Hirotaka Osawa, Takashi Otsuki, and Fujio Toriumi. 2024. AIWolfDial 2024: Summary of Natural Language Division of 6th International AIWolf Contest. In Proceedings of the 2nd International AIWolfDial Workshop, pages 1–12, Tokyo, Japan. Association for Computational Linguistics. 2024/9/24
Yoshinobu Kano, Neo Watanabe, Kaito Kagaminuma, Claus Aranha, Jaewon Lee, Benedek Hauer, Hisaichi Shibata, Soichiro Miki, Yuta Nakamura, Takuya Okubo, Soga Shigemura, Rei Ito, Kazuki Takashima, Tomoki Fukuda, Masahiro Wakutani, Tomoya Hatanaka, Mami Uchida, Mikio Abe, Akihiro Mikami, Takashi Otsuki, Zhiyang Qi, Michimasa Inaba, Kei Harada, Daisuke Katagami, Hirotaka Osawa, Fujio Toriumi. AIWolfDial 2023: Summary of Natural Language Division of 5th International AIWolf Contest. The 16th International Natural Language Generation Conference (INLG 2023). Prague, Czech Republic. 2023/9/14
Yoshinobu Kano, Claus Aranha, Michimasa Inaba, Fujio Toriumi, Hirotaka Osawa, Daisuke Katagami, Takashi Otsuki, Issei Tsunoda, Shoji Nagayama, Dolça Tellols, Yu Sugawara and Yohei Nakata. Overview of AIWolfDial 2019 Shared Task: Contest of Automatic Dialog Agents to Play the Werewolf Game through Conversations. The 1st International Workshop of AI Werewolf and Dialog System (AIWolfDial2019) Collocated with INLG 2019 conference. 2019/10/29
Other
渡邉嶺王, 狩野芳伸. プレイヤー間の論理的情報を与えたLLMによる人狼ゲーム対話エージェントの構築 [Building a Werewolf Game Dialogue Agent Using an LLM Provided with Logical Information Between Players]. The 31st Annual Meeting of the Association for Natural Language Processing (NLP2025). Dejima Messe Nagasaki. 2025/3/12
Yuka Tsubota, Yoshinobu Kano. Text Generation Indistinguishable from Target Person by Prompting Few Examples Using LLM. The 2nd International AIWolfDial Workshop, pages 13–20, Tokyo, Japan. Association for Computational Linguistics. 2024/9/24
Neo Watanabe, Yoshinobu Kano. Werewolf Game Agent by Generative AI Incorporating Logical Information Between Players. The 2nd International AIWolfDial Workshop, pages 21–29, Tokyo, Japan. Association for Computational Linguistics. 2024/9/24
渡邉嶺王, 狩野芳伸. プレイヤー間の論理的情報を与えた生成AIの対話による人狼ゲームエージェントの構築 [Building a Werewolf Game Agent Using Generative AI Dialogue with Logical Information Between Players]. The 38th Annual Conference of the Japanese Society for Artificial Intelligence (JSAI 2024). Act City Hamamatsu. 2024/5/30
角田一星, 狩野芳伸. 人狼知能開発のためのドメイン特化事前学習モデルの作成 [Creating a Domain-Specific Pre-trained Model for AIWolf Development]. The 27th Annual Meeting of the Association for Natural Language Processing (NLP2021). Online. 2021/3/16
三原直樹, 狩野芳伸. 人狼知能における自然な雑談の生成 [Generating Natural Small Talk in AIWolf]. Informatics Symposium (2020). Online. 2020/12/25
箕輪 峻，狩野 芳伸. 人狼ゲームにおける対話システムのための中間表現および自然言語から中間表現への変換 [An Intermediate Representation for Dialogue Systems in the Werewolf Game and Its Conversion from Natural Language]. Journal of the Japanese Society for Artificial Intelligence, Vol. 35, No. 1, Special Issue on “Intelligent Dialogue Systems”. DOI: https://doi.org/10.1527/tjsai.DSI-F 2020/1/1
Issei Tsunoda and Yoshinobu Kano. AI Werewolf Agent with Reasoning Using Role Patterns and Heuristics. The 1st International Workshop of AI Werewolf and Dialog System (AIWolfDial2019) Collocated with INLG 2019 conference. 2019/10/29
箕輪峻, 滝波秋穂, 小川ちひろ, 三原直樹, 真木裕子, 柴淳, 狩野芳伸. プロトコルを用いた意味理解による人狼知能の自然言語エージェント [A Natural Language AIWolf Agent with Semantic Understanding Using Protocols]. The 8th Dialogue System Symposium, SIG on Spoken Language Understanding and Dialogue Processing (SLUD), JSAI, 81st Meeting. 2017/10/12
箕輪峻, 狩野芳伸, 柴淳, 黒田和也. 係り受け関係を利用したルールベースによる自然言語人狼エージェントの構築 [Building a Rule-Based Natural Language Werewolf Agent Using Dependency Relations]. The 2nd Game AI Tournament (GAT 2017). The University of Electro-Communications. 2017/3/9
箕輪峻, 狩野芳伸. 複数のルールによる評価を総合的に判断する人狼エージェントの実装 [Implementation of a Werewolf Agent That Comprehensively Judges Multiple Rule-Based Evaluations]. Game AI Tournaments, 1st Tournament (GAT 2016). The University of Electro-Communications. 2016/3/9