paper-with-me

홈 › Papers

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

2025-10-20 · Patricia Delafuente, Arya Honraopatil, Lara J. Martin arxiv

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.

📄 PDF Abstract BibTeX arXiv:2510.18112

Code (0)

등록된 구현이 없습니다.

Tasks

Prompt Engineering

Similar Papers 제목 키워드 기반

First Steps Towards Overhearing LLM Agents: A Case Study With Dungeons & Dragons Gameplay

2025-05-28 · Andrew Zhu, Evan Osgood, Chris Callison-Burch

Much work has been done on conversational LLM agents which directly assist human users with tasks. We present an alternative paradigm for interacting with LLM agents, which we call "overhearing agents". These overhearing…

Two-step Constructive Approaches for Dungeon Generation

2019-06-11 · Michael Cerny Green, Ahmed Khalifa, Athoug Alsoughayer, Divyesh Surana 외

This paper presents a two-step generative approach for creating dungeons in the rogue-like puzzle game MiniDungeons 2. Generation is split into two steps, initially producing the architectural layout of the level as its …

PositionVocal Bursts Valence Prediction

Storytelling with Dialogue: A Critical Role Dungeons and Dragons Dataset

2020-07-01 · ACL 2020 6 · Revanth Rameshkumar, Peter Bailey

This paper describes the Critical Role Dungeons and Dragons Dataset (CRD3) and related analyses. Critical Role is an unscripted, live-streamed show where a fixed group of people play Dungeons and Dragons, an open-ended r…

Abstractive Text SummarizationData Augmentation

Generative Adversarial Network Rooms in Generative Graph Grammar Dungeons for The Legend of Zelda

2020-01-14 · Jake Gutierrez, Jacob Schrum

Generative Adversarial Networks (GANs) have demonstrated their ability to learn patterns in data and produce new exemplars similar to, but different from, their training set in several domains, including video games. How…

Generative Adversarial Network

Generating Descriptive and Rules-Adhering Spells for Dungeons & Dragons Fifth Edition

2022-06-01 · games (LREC) 2022 6 · Pax Newman, Yudong Liu

We examine the task of generating unique content for the spell system of the tabletop roleplaying game Dungeons and Dragons Fifth Edition using several generative language models. Due to the descriptive nature of the gam…

Descriptive