Enhancing Consistency of Werewolf AI through Dialogue Summarization and Persona Information

Yoshiki Tanaka, Takumasa Kaneko, Hiroki Onozeki, Natsumi Ezure, Ryuichi Uehara +4 more
3/7/2026
cs.CLcs.AI

No confident code implementation found for this paper.

Abstract

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.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Enhancing Dialogue Generation in Werewolf Game Through Situation Analysis and Persuasion Strategies

91% match2024

An Implementation of Werewolf Agent That does not Truly Trust LLMs

89% match2024

Verbal Werewolf: Engage Users with Verbalized Agentic Werewolf Game Framework

88% match2025

Strategy Adaptation in Large Language Model Werewolf Agents

84% match2025

Who Speaks Next? Multi-party AI Discussion Leveraging the Systematics of Turn-taking in Murder Mystery Games

83% match1 repo22024

WereWolf-Plus: An Update of Werewolf Game setting Based on DSGBench

82% match2025

Cite this paper

@article{tanaka2026enhancing,
  title  = {Enhancing Consistency of Werewolf AI through Dialogue Summarization and Persona Information},
  author = {Yoshiki Tanaka and Takumasa Kaneko and Hiroki Onozeki and Natsumi Ezure and Ryuichi Uehara and Zhiyang Qi and Tomoya Higuchi and Ryutaro Asahara and Michimasa Inaba},
  year   = {2026},
  eprint = {2603.07111},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2603.07111v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2603.07111.svg)](https://codeofpaper.com/paper/2603.07111)

Discussion