Does Reasoning Help LLM Agents Play Dungeons and Dragons? A Prompt Engineering Experiment

Patricia Delafuente, Arya Honraopatil, Lara J. Martin
10/20/2025
cs.CL

No confident code implementation found for this paper.

Abstract

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.

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

Enhance Reasoning for Large Language Models in the Game Werewolf

84% match1 repo292024

GAMEBoT: Transparent Assessment of LLM Reasoning in Games

84% match1 repo352024

Playing With AI: How Do State-Of-The-Art Large Language Models Perform in the 1977 Text-Based Adventure Game Zork?

84% match2026

GameArena: Evaluating LLM Reasoning through Live Computer Games

84% match1 repo92024

GameArena: Evaluating LLM Reasoning through Live Computer Games

84% match1 repo92024

IDEA: Enhancing the Rule Learning Ability of Large Language Model Agent through Induction, Deduction, and Abduction

83% match1 repo62024

Cite this paper

@article{delafuente2025does,
  title  = {Does Reasoning Help LLM Agents Play Dungeons and Dragons? A Prompt Engineering Experiment},
  author = {Patricia Delafuente and Arya Honraopatil and Lara J. Martin},
  year   = {2025},
  eprint = {2510.18112},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2510.18112v1}
}

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/2510.18112.svg)](https://codeofpaper.com/paper/2510.18112)

Discussion