Workshop Program
September 24th Tuesday, 2024 at AIST Tokyo Waterfront
Access Map in English and Japanese
Registered participants will be invited to our formal Slack channel.
12:20-12:25 Opening
Opening: what is AIWolf? (Yoshinobu Kano)
12:25-13:45 Oral presentations (1): peer reviewed papers
Verification of Reasoning Ability using BDI Logic and Large Language Model in AIWolf (Hiraku Gondo, Hiroki Sakaji and Itsuki Noda)
Text Generation Indistinguishable from Target Person by Prompting Few Examples Using LLM (Yuka Tsubota and Yoshinobu Kano)
An Implementation of Werewolf Agent That does not Truly Trust LLMs (Takehiro Sato, Shintaro Ozaki and Daisaku Yokoyama)
13:45-13:55 Short break
13:55-15:10 Oral presentation (2): peer reviewed papers
Werewolf Game Agent by Generative AI Incorporating Logical Information Between Players (Neo Watanabe and Yoshinobu Kano)
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 and Michimasa Inaba)
Enhancing Dialogue Generation in Werewolf Game Through Situation Analysis and Persuasion Strategies (Zhiyang Qi and Michimasa Inaba)
15:10-15:40 Coffee break
15:40-16:20 System presentation: non-archival AIWolf agent descriptions
GPTaku (Takuma Okada and Takeshi Ito)
HondaNLP: Exploring Approaches to Force a Werewolf’s Confession via Prompt Injection by the Seer in the Werewolf Game (Shotaro Nishimura, Kazuki Yoshigai, Tameaki Honda, Ko Uchida, Hiroshi Honda)
Teams of IS_lab, kanolab, satozaki, UEC_IL will explain their systems in the oral presentation sessions as a peer reviewed papers.
16:20-16:30 Short break
16:30-17:25 Evaluations and award ceremony
Sponser award with talk (Yuuichi Sasaki)
Evaluation, analysis and awards (Organizers)
17:25-18:25 Demonstration and Discussion
18:25-18:30 Closing
19:00- Informal workshop dinner (prior registeration required via Slack)