Work

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

Year: 2025

Type: article

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.

Source: Maryland Shared Open Access Repository (USMAI Consortium)

DOI: 10.13016/m26v97-axw8

Authors: Delafuente, Patricia J, Honraopatil, Arya, Martin, Lara J.

Language: English

Topic: Artificial Intelligence in Games

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W7134063209

FWCI:

Cites:

Cited by:

Related to: