Enhancing Consistency of Werewolf AI through Dialogue Summarization and Persona Information
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911495512653824 |
|---|---|
| author | Tanaka, Yoshiki Kaneko, Takumasa Onozeki, Hiroki Ezure, Natsumi Uehara, Ryuichi Qi, Zhiyang Higuchi, Tomoya Asahara, Ryutaro Inaba, Michimasa |
| author_facet | Tanaka, Yoshiki Kaneko, Takumasa Onozeki, Hiroki Ezure, Natsumi Uehara, Ryuichi Qi, Zhiyang Higuchi, Tomoya Asahara, Ryutaro Inaba, Michimasa |
| contents | 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 years, large language models like ChatGPT have garnered attention for their exceptional response generation and reasoning capabilities. We thus develop the LLM-based agents for the Werewolf Game. This study aims to enhance the consistency of the agent's utterances by utilizing dialogue summaries generated by LLMs and manually designed personas and utterance examples. By analyzing self-match game logs, we demonstrate that the agent's utterances are contextually consistent and that the character, including tone, is maintained throughout the game. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_07111 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Enhancing Consistency of Werewolf AI through Dialogue Summarization and Persona Information Tanaka, Yoshiki Kaneko, Takumasa Onozeki, Hiroki Ezure, Natsumi Uehara, Ryuichi Qi, Zhiyang Higuchi, Tomoya Asahara, Ryutaro Inaba, Michimasa Computation and Language Artificial Intelligence 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 years, large language models like ChatGPT have garnered attention for their exceptional response generation and reasoning capabilities. We thus develop the LLM-based agents for the Werewolf Game. This study aims to enhance the consistency of the agent's utterances by utilizing dialogue summaries generated by LLMs and manually designed personas and utterance examples. By analyzing self-match game logs, we demonstrate that the agent's utterances are contextually consistent and that the character, including tone, is maintained throughout the game. |
| title | Enhancing Consistency of Werewolf AI through Dialogue Summarization and Persona Information |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2603.07111 |