# An Implementation of Werewolf Agent That does not Truly Trust LLMs

arXiv: https://arxiv.org/abs/2409.01575 · HTML: https://mlsanity.com/paper/2409.01575/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning for LLM agents, one of 16 directions in LLM agents and tool use.
- Builds on 6 of its 20 references that are in the map.
- First posted on arXiv 3 Sep 2024.

## Placed in

- LLM agents and tool use / [Reinforcement learning for LLM agents](https://mlsanity.com/agents/reinforcement-learning-for-llm-agents/)

## Builds on (most cited first, 6 of 6)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT](https://mlsanity.com/paper/2302.11382/) (2023)
- [Exploring Large Language Models for Communication Games: An Empirical Study on Werewolf](https://mlsanity.com/paper/2309.04658/) (2023)
- [Dungeons and Dragons as a Dialog Challenge for Artificial Intelligence](https://mlsanity.com/paper/2210.07109/) (2022)
- [Hybrid LLM/Rule-based Approaches to Business Insights Generation from Structured Data](https://mlsanity.com/paper/2404.15604/) (2024)

## Built on by (most cited first, 3 of 3)

- [Multi-agent KTO: Reinforcing Strategic Interactions of Large Language Model in Language Game](https://mlsanity.com/paper/2501.14225/) (2025)
- [Shall We Play a Game? Language Models for Open-ended Wargames](https://mlsanity.com/paper/2509.17192/) (2025)
- [Can LLMs Play O uAn Quan Game? A Study of Multi-Step Planning and Decision Making](https://mlsanity.com/paper/2507.03711/) (2025)

## Abstract (arXiv)

Werewolf is an incomplete information game, which has several challenges when creating a computer agent as a player given the lack of understanding of the situation and individuality of utterance (e.g., computer agents are not capable of characterful utterance or situational lying). We propose a werewolf agent that solves some of those difficulties by combining a Large Language Model (LLM) and a rule-based algorithm. In particular, our agent uses a rule-based algorithm to select an output either from an LLM or a template prepared beforehand based on the results of analyzing conversation history using an LLM. It allows the agent to refute in specific situations, identify when to end the conversation, and behave with persona. This approach mitigated conversational inconsistencies and facilitated logical utterance as a result. We also conducted a qualitative evaluation, which resulted in our agent being perceived as more human-like compared to an unmodified LLM. The agent is freely available for contributing to advance the research in the field of Werewolf game.