This paper explores the application of Large Language Models (LLMs) and reasoning to predict Dungeons & Dragons (DnD) player actions and format them as Avrae Discord bot commands. Using the FIREBALL dataset, we evaluated a reasoning model, DeepSeek-R1-Distill-LLaMA-8B, and an instruct model, LLaMA-3.1-8B-Instruct, for command generation. Our findings highlight the importance of providing specific instructions to models, that even single sentence changes in prompts can greatly affect the output of models, and that instruct models are sufficient for this task compared to reasoning models.
@article{arxiv.2510.18112,
title = {Does Reasoning Help LLM Agents Play Dungeons and Dragons? A Prompt Engineering Experiment},
author = {Patricia Delafuente and Arya Honraopatil and Lara J. Martin},
journal= {arXiv preprint arXiv:2510.18112},
year = {2025}
}
Comments
Published at the Wordplay: When Language Meets Games Workshop (EMNLP 2025)