# Dungeons and Dragons as a Dialog Challenge for Artificial Intelligence

arXiv: https://arxiv.org/abs/2210.07109 · HTML: https://mlsanity.com/paper/2210.07109/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 46 references that are in the map.
- First posted on arXiv 13 Oct 2022.

## Builds on (most cited first, 29 of 29)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [LaMDA: Language Models for Dialog Applications](https://mlsanity.com/paper/2201.08239/) (2022)
- [Hierarchical Neural Story Generation](https://mlsanity.com/paper/1805.04833/) (2018)
- [DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation](https://mlsanity.com/paper/1911.00536/) (2019)
- [Personalizing Dialogue Agents: I have a dog, do you have pets too?](https://mlsanity.com/paper/1801.07243/) (2018)
- [CTRL: A Conditional Transformer Language Model for Controllable Generation](https://mlsanity.com/paper/1909.05858/) (2019)
- [Towards a Human-like Open-Domain Chatbot](https://mlsanity.com/paper/2001.09977/) (2020)
- [AllenNLP: A Deep Semantic Natural Language Processing Platform](https://mlsanity.com/paper/1803.07640/) (2018)
- [Deep Reinforcement Learning for Dialogue Generation](https://mlsanity.com/paper/1606.01541/) (2016)
- [Plan-And-Write: Towards Better Automatic Storytelling](https://mlsanity.com/paper/1811.05701/) (2018)
- [Learning to Speak and Act in a Fantasy Text Adventure Game](https://mlsanity.com/paper/1903.03094/) (2019)
- [Keep CALM and Explore: Language Models for Action Generation in Text-based Games](https://mlsanity.com/paper/2010.02903/) (2020)
- [PlotMachines: Outline-Conditioned Generation with Dynamic Plot State Tracking](https://mlsanity.com/paper/2004.14967/) (2020)
- [Do Massively Pretrained Language Models Make Better Storytellers?](https://mlsanity.com/paper/1909.10705/) (2019)
- [Event Representations for Automated Story Generation with Deep Neural Nets](https://mlsanity.com/paper/1706.01331/) (2017)
- [STORIUM: A Dataset and Evaluation Platform for Machine-in-the-Loop Story Generation](https://mlsanity.com/paper/2010.01717/) (2020)
- [Controlling Style in Generated Dialogue](https://mlsanity.com/paper/2009.10855/) (2020)
- [How to Motivate Your Dragon: Teaching Goal-Driven Agents to Speak and Act in Fantasy Worlds](https://mlsanity.com/paper/2010.00685/) (2020)
- [Inferring the Reader: Guiding Automated Story Generation with Commonsense Reasoning](https://mlsanity.com/paper/2105.01311/) (2021)
- [Hierarchical Reinforcement Learning for Open-Domain Dialog](https://mlsanity.com/paper/1909.07547/) (2019)
- [Playing Text-Based Games with Common Sense](https://mlsanity.com/paper/2012.02757/) (2020)
- ["My Way of Telling a Story": Persona based Grounded Story Generation](https://mlsanity.com/paper/1906.06401/) (2019)
- [Toward Automated Quest Generation in Text-Adventure Games](https://mlsanity.com/paper/1909.06283/) (2019)
- [Generative Deep Neural Networks for Dialogue: A Short Review](https://mlsanity.com/paper/1611.06216/) (2016)
- [Generating Interactive Worlds with Text](https://mlsanity.com/paper/1911.09194/) (2019)
- [DiSCoL: Toward Engaging Dialogue Systems through Conversational Line Guided Response Generation](https://mlsanity.com/paper/2102.02191/) (2021)
- [Collaborative Storytelling with Human Actors and AI Narrators](https://mlsanity.com/paper/2109.14728/) (2021)
- [Shaping the Narrative Arc: An Information-Theoretic Approach to Collaborative Dialogue](https://mlsanity.com/paper/1901.11528/) (2019)
- [Where is the context? -- A critique of recent dialogue datasets](https://mlsanity.com/paper/2004.10473/) (2020)

## Built on by (most cited first, 30 of 35)

- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Character-LLM: A Trainable Agent for Role-Playing](https://mlsanity.com/paper/2310.10158/) (2023)
- [From Web Search towards Agentic Deep Research: Incentivizing Search with Reasoning Agents](https://mlsanity.com/paper/2506.18959/) (2025)
- [Oolong: Evaluating Long Context Reasoning and Aggregation Capabilities](https://mlsanity.com/paper/2511.02817/) (2025)
- [Interactive Natural Language Processing](https://mlsanity.com/paper/2305.13246/) (2023)
- [Theory of Mind in Large Language Models: Assessment and Enhancement](https://mlsanity.com/paper/2505.00026/) (2025)
- [CALYPSO: LLMs as Dungeon Masters' Assistants](https://mlsanity.com/paper/2308.07540/) (2023)
- [I Cast Detect Thoughts: Learning to Converse and Guide with Intents and Theory-of-Mind in Dungeons and Dragons](https://mlsanity.com/paper/2212.10060/) (2022)
- [Modeling Cross-Cultural Pragmatic Inference with Codenames Duet](https://mlsanity.com/paper/2306.02475/) (2023)
- [FIREBALL: A Dataset of Dungeons and Dragons Actual-Play with Structured Game State Information](https://mlsanity.com/paper/2305.01528/) (2023)
- [Word2World: Generating Stories and Worlds through Large Language Models](https://mlsanity.com/paper/2405.06686/) (2024)
- [An Appraisal-Based Chain-Of-Emotion Architecture for Affective Language Model Game Agents](https://mlsanity.com/paper/2309.05076/) (2023)
- [Ontologically Faithful Generation of Non-Player Character Dialogues](https://mlsanity.com/paper/2212.10618/) (2022)
- [CoRRPUS: Code-based Structured Prompting for Neurosymbolic Story Understanding](https://mlsanity.com/paper/2212.10754/) (2022)
- [Large Language Models as Minecraft Agents](https://mlsanity.com/paper/2402.08392/) (2024)
- [Thespian: Multi-Character Text Role-Playing Game Agents](https://mlsanity.com/paper/2308.01872/) (2023)
- [AgentGroupChat: An Interactive Group Chat Simulacra For Better Eliciting Emergent Behavior](https://mlsanity.com/paper/2403.13433/) (2024)
- [Time to Talk: LLM Agents for Asynchronous Group Communication in Mafia Games](https://mlsanity.com/paper/2506.05309/) (2025)
- [FaST: Feature-aware Sampling and Tuning for Personalized Preference Alignment with Limited Data](https://mlsanity.com/paper/2508.04698/) (2025)
- [Tachikuma: Understading Complex Interactions with Multi-Character and Novel Objects by Large Language Models](https://mlsanity.com/paper/2307.12573/) (2023)
- [A LLM Benchmark based on the Minecraft Builder Dialog Agent Task](https://mlsanity.com/paper/2407.12734/) (2024)
- [You Have Thirteen Hours in Which to Solve the Labyrinth: Enhancing AI Game Masters with Function Calling](https://mlsanity.com/paper/2409.06949/) (2024)
- [RESPONSE: Benchmarking the Ability of Language Models to Undertake Commonsense Reasoning in Crisis Situation](https://mlsanity.com/paper/2503.11348/) (2025)
- [Skill Check: Some Considerations on the Evaluation of Gamemastering Models for Role-playing Games](https://mlsanity.com/paper/2309.13702/) (2023)
- [PANGeA: Procedural Artificial Narrative using Generative AI for Turn-Based Video Games](https://mlsanity.com/paper/2404.19721/) (2024)
- [An Implementation of Werewolf Agent That does not Truly Trust LLMs](https://mlsanity.com/paper/2409.01575/) (2024)
- [AntEval: Evaluation of Social Interaction Competencies in LLM-Driven Agents](https://mlsanity.com/paper/2401.06509/) (2024)
- [Using Natural Language Inference to Improve Persona Extraction from Dialogue in a New Domain](https://mlsanity.com/paper/2401.06742/) (2024)
- [SAGA: A Participant-specific Examination of Story Alternatives and Goal Applicability for a Deeper Understanding of Complex Events](https://mlsanity.com/paper/2408.05793/) (2024)
- [PAYADOR: A Minimalist Approach to Grounding Language Models on Structured Data for Interactive Storytelling and Role-playing Games](https://mlsanity.com/paper/2504.07304/) (2025)

## Abstract (arXiv)

AI researchers have posited Dungeons and Dragons (D&D) as a challenge problem to test systems on various language-related capabilities. In this paper, we frame D&D specifically as a dialogue system challenge, where the tasks are to both generate the next conversational turn in the game and predict the state of the game given the dialogue history. We create a gameplay dataset consisting of nearly 900 games, with a total of 7,000 players, 800,000 dialogue turns, 500,000 dice rolls, and 58 million words. We automatically annotate the data with partial state information about the game play. We train a large language model (LM) to generate the next game turn, conditioning it on different information. The LM can respond as a particular character or as the player who runs the game--i.e., the Dungeon Master (DM). It is trained to produce dialogue that is either in-character (roleplaying in the fictional world) or out-of-character (discussing rules or strategy). We perform a human evaluation to determine what factors make the generated output plausible and interesting. We further perform an automatic evaluation to determine how well the model can predict the game state given the history and examine how well tracking the game state improves its ability to produce plausible conversational output.