ワークショップ プログラム(仮)
2026 年 10 月 17 日(土)9:00–12:30、Wachtkammer 3e Klasse(オランダ・ユトレヒト)/ オンライン https://2026.inlgmeeting.org/
時刻はすべて中央ヨーロッパ夏時間(CEST、UTC+2)です。日本時間は +7 時間(16:00–19:30)です。
Session 1〜3 の発表はすべてワークショップに採択された査読付き論文(peer reviewed papers)です。Long は 15 分、Short は 10 分の発表(質疑込み)です。発表者には * を付けています。仮プログラムのため変更の可能性があります。英語版もあります。
09:00–09:15 オープニング・コンテスト結果報告
- オープニング: 人狼知能とは(狩野芳伸)
- AIWolfDial 2026: 2026 年人狼知能国際大会 自然言語部門の結果報告
09:15–09:35 参加チーム発表(6 件): 論文なしの参加チームによるエージェント紹介(non-archival)、各 3 分
- Team kataken14f (Atsuro Hamanaka, Ariana Sheikhi, Daiki Asakura, Ryosuke Sueyoshi*)
- Team CamelliaDragons (Momoka Kato*, Kaito Okuno, Syuji Otsuki, Keita Kasuya, Toma Inagaki)
- Team CanisLupus (Yu Sugawara*)
- Team gotsumori-NLP (Tatsuya Mikami*)
- Team SunameLLi (Satoko Natsubori*, Hiroki Nakanishi, Soichiro Mikami)
- Team wool_100% (Kento Fukuda*)
09:35–10:15 Session 1 — 自己改善と学習: peer reviewed papers(査読付き論文)
- 09:35 [Long] Self-Improvement of AIWolf Agents Based on Self-Play Logs (Taku Umeda*, Takao Endo, Jumpei Hato, Kotaro Otomura) (Team AGKAI)
- 09:50 [Long] Do Cross-Game Lessons Appear in Later Dialogue? A Controlled Measurement of Lesson Realization in Werewolf Dialogue Agents (Kota Munaoka*, Yoshinobu Kano) (Team Oxymoron)
- 10:05 [Short] The moon is new each night: enhancing reasoning with self-reflection in the game of Werewolf (Alicja Kasicka*, Łukasz Krajewski, Bartosz Przybył, Natalia Krawczyk, Michał Szczerbak, Justyna Gromada) (Team carrot)
10:15–10:35 休憩
10:35–11:20 Session 2 — 役割別戦略と一貫性: peer reviewed papers(査読付き論文)
- 10:35 [Long] Power Play Instructions in LLM Werewolf: Cross-Request Execution and Game Outcomes (Shoma Yato*, Ikumu Komatsu, Haruka Itakura, Daisuke Katagami) (Team yatolab)
- 10:50 [Short] An AIWolf Agent for Consistent Dialogue with Role-Specific Strategies and Utterance Regeneration (Yuki Kubo*, Taiga Sano, Eiji Kumakawa, Tae Sato) (Team NTT-HAI)
- 11:00 [Short] Improving Dialogues in LLM-Based AI Werewolf Agents with Few-Shot Discussion Examples (Yuya Harada*, Yoshinobu Kano) (Team yharada)
- 11:10 [Short] Keeping a Public Story Straight: Memory Interventions for LLM Agents in AIWolf (Ryan Lee*) (Team ryanleeai)
11:20–12:20 Session 3 — タイミング・個性・評価・頑健性: peer reviewed papers(査読付き論文)
- 11:20 [Long] Beyond What to Say: Proactive Utterance Timing with Inner Thoughts for Werewolf Agents (Yoshiki Tanaka*, Shuya Uchiyama, Daichi Hamaguchi, Michimasa Inaba) (Team UEC-IL)
- 11:35 [Long] Preserving Character in Four Letters: Personality Information Compression in AIWolf Agents Using MBTI-like Labels (Ryosuke Sueyoshi, Kentaro Hoshi*, Miyu Ueki, Chaeyoung Sung) (Team noisy_watcher)
- 11:50 [Long] Fine-Grained Absolute Evaluation of Utterance Naturalness in Japanese AIWolf Dialogue: An Agreement Analysis between Human Annotators and LLM Judges (Chaeyoung Sung*, Ryosuke Sueyoshi, Kentaro Hoshi, Miyu Ueki, Masato Taki) (Team noisy_watcher)
- 12:05 [Long] What Breaks Prompt-Specified Settings in Multi-Turn Dialogue Attacks: Attack Type, Burst-Injection Granularity, and Role Boundaries (Yuki Shimoda*, Yoshinobu Kano) (Team yshimoda)
12:20–12:30 クロージング・総合討論
(終了後、会場で昼食が提供されます。)