Enhancing Consistency of Werewolf AI through Dialogue Summarization and Persona Information

TL;DR

This paper introduces a Werewolf AI that uses dialogue summarization and persona information to improve consistency and character maintenance during gameplay, leveraging large language models for enhanced reasoning and response generation.

Contribution

The study develops an LLM-based Werewolf AI that employs dialogue summaries and persona data to ensure consistent character portrayal and reasoning in the game.

Findings

The AI maintains character consistency throughout the game.

Dialogue summarization improves response relevance and coherence.

The approach enhances the AI's reasoning and communication skills.

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.