CALYPSO: LLMs as Dungeon Master's Assistants
Open accessAbstract
The role of a Dungeon Master, or DM, in the game Dungeons & Dragons is to perform multiple tasks simultaneously. The DM must digest information about the game setting and monsters, synthesize scenes to present to other players, and respond to the players' interactions with the scene. Doing all of these tasks while maintaining consistency within the narrative and story world is no small feat of human cognition, making the task tiring and unapproachable to new players. Large language models (LLMs) like GPT-3 and ChatGPT have shown remarkable abilities to generate coherent natural language text. In this paper, we conduct a formative evaluation with DMs to establish the use cases of LLMs in D&D and tabletop gaming generally. We introduce CALYPSO, a system of LLM-powered interfaces that support DMs with information and inspiration specific to their own scenario. CALYPSO distills game context into bite-sized prose and helps brainstorm ideas without distracting the DM from the game. When given access to CALYPSO, DMs reported that it generated high-fidelity text suitable for direct presentation to players, and low-fidelity ideas that the DM could develop further while maintaining their creative agency. We see CALYPSO as exemplifying a paradigm of AI-augmented tools that provide synchronous creative assistance within established game worlds, and tabletop gaming more broadly.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
CALYPSO distills lengthy game contexts into bite-sized prose, preserving critical story state accessibility.
“In narrative domains, CALYPSO (Zhu et al., 2023) distills lengthy game contexts into bite-sized prose, preserving critical story state accessibility.”
From Memory in the Age of AI Agents (2025) · cites this paper as Zhu et al., 2023
The Abstract says CALYPSO distills game context into bite-sized prose, and §4.1 describes condensing encounter details and monster lore. The Abstractive Understanding passage says a summary helps the DM refer back to CALYPSO’s ideas, aiding continuity. The paper does not establish that CALYPSO preserves critical story state more broadly or keeps it accessible across the game. (LLM, conf=0.84)
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404 · see citing works
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372 · see citing works
The Curious Case of Neural Text Degeneration
Holtzman, A., Buys, J., Du, L., Forbes, M., & Choi, Y. (2019) · arXiv · doi:10.48550/arxiv.1904.09751 · Cited by 1,304 · see citing works
TaleBrush: Sketching Stories with Generative Pretrained Language Models
Chung, J. J. Y., Kim, W., Yoo, K. M., Lee, H., Adar, E., & Chang, M. (2022) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3491102.3501819 · Cited by 206 · see citing works
STORIUM: A Dataset and Evaluation Platform for Machine-in-the-Loop Story Generation
Akoury, N., Wang, S., Whiting, J., Hood, S., Peng, N., & Iyyer, M. (2020) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.525 · Cited by 85 · see citing works
Creative Help: A Story Writing Assistant
Roemmele, M., & Gordon, A. S. (2015) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-27036-4_8 · Cited by 83 · see citing works
Creative Writing with an AI-Powered Writing Assistant: Perspectives from Professional Writers
Ippolito, D., Yuan, A., Coenen, A., & Burnam, S. (2022) · arXiv · doi:10.48550/arxiv.2211.05030 · Cited by 52 · see citing works
Yuan, Y., Cao, J., Wang, R., et al. (2021) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3411764.3445512 · Cited by 43 · see citing works
Storytelling with Dialogue: A Critical Role Dungeons and Dragons Dataset
Rameshkumar, R., & Bailey, P. (2020) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2020.acl-main.459 · Cited by 37 · see citing works
The Design of Writing Buddy: A Mixed-Initiative Approach Towards Computational Story Collaboration
Samuel, B., Mateas, M., & Wardrip-Fruin, N. (2016) · International Conference on Interactive Digital Storytelling · doi:10.1007/978-3-319-48279-8_34 · Cited by 33 · see citing works
Dungeons and Dragons as a Dialog Challenge for Artificial Intelligence
Callison-Burch, C., Tomar, G. S., Martin, L. J., Ippolito, D., Bailis, S., & Reitter, D. (2022) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2022.emnlp-main.637 · Cited by 30 · see citing works
Self-citationLoose Ends: A Mixed-Initiative Creative Interface for Playful Storytelling
Kreminski, M., Dickinson, M., Wardrip-Fruin, N., & Mateas, M. (2022) · Artificial Intelligence and Interactive Digital Entertainment Conference · doi:10.1609/aiide.v18i1.21955 · Cited by 27 · see citing works
Deep Dungeons and Dragons: Learning Character-Action Interactions from Role-Playing Game Transcripts
Louis, A., & Sutton, C. A. (2018) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/n18-2111 · Cited by 17 · see citing works
Zhou, P., Zhu, A., Hu, J., Pujara, J., Ren, X., Callison-Burch, C., Choi, Y., & Ammanabrolu, P. (2023) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2023.acl-long.624 · Cited by 16 · see citing works
Self-citationTowards Computational Support with Language Models for TTRPG Game Masters
Kelly, J., Mateas, M., & Wardrip–Fruin, N. (2023) · International Conference on the Foundations of Digital Games (FDG) · doi:10.1145/3582437.3587202 · Cited by 15 · see citing works
Creative Wand: A System to Study Effects of Communications in Co-creative Settings
Lin, Z., Agarwal, R., & Riedl, M. O. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment · doi:10.1609/aiide.v18i1.21946 · Cited by 9 · see citing works
Table-Top Gaming Narratology for Digital Interactive Storytelling
van Velsen, M., Williams, J., & Verhulsdonck, G. (2009) · Lecture notes in computer science · doi:10.1007/978-3-642-10643-9_15 · Cited by 8 · see citing works
A Synset-Based Recommender Method for Mixed-Initiative Narrative World Creation
Perez, M. R. B., Eisemann, E., & Bidarra, R. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-92300-6_2 · Cited by 7 · see citing works
Rolling the Dice: Imagining Generative AI as a Dungeons & Dragons Storytelling CompanionPreprint
Santiago, J. M., Parayno, R. L., Deja, J. A., et al. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2304.01860 · Cited by 3 · see citing works
Interviews Towards Designing Support Tools for TTRPG Game Masters
Acharya, D., Mateas, M., & Wardrip-Fruin, N. (2021) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-92300-6_26
Bringing Stories Alive: Generating Interactive Fiction Worlds
Ammanabrolu, P., Cheung, W., Tu, D., Broniec, W., & Riedl, M. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment · doi:10.1609/aiide.v16i1.7400
Framing Storytelling with Games
Bergström, K. (2011) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-25289-1_19
FIREBALL: A Dataset of Dungeons and Dragons Actual-Play with Structured Game State Information
Zhu, A., Aggarwal, K., Feng, A., Martin, L., & Callison-Burch, C. (2023) · Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2023.acl-long.229
Self-citation
Flagged first, then by citations
Research works printed but not linked: 7
- In Si, M.; Thue, D.; André, E.; Lester, J. C.; Tanenbaum, T. J.; and Zammitto, V., eds., Interactive Storytelling, Lec- ture Notes in Computer Science, 170-181. Berlin, Heidel- berg: Springer. ISBN 978-3-642-25289-1.
- Calderwood, A.; Qiu, V.; Gero, K. I.; and Chilton, L. B. 2020. How Novelists Use Generative Language Models: An Exploratory User Study. In International Conference on Intelligent User Interfaces (IUI) Workshops. Cagliari, Italy: ACM.
- Coenen, A.; Davis, L.; Ippolito, D.; Reif, E.; and Yuan, A. 2021. Wordcraft: a Human-AI Collaborative Editor for Story Writing. In First Workshop on Bridging Human- Computer Interaction and Natural Language Processing at EACL 2021. Association for Computational Linguistics.
- Martin, L. J.; Sood, S.; and Riedl, M. O. 2018. Dungeons and DQNs: Toward Reinforcement Learning Agents that Play Tabletop Roleplaying Games. In Wu, H.-Y.; Si, M.; and Jhala, A., eds., Joint Workshop on Intelligent Narra- tive Technologies and Workshop on Intelligent Cinematog- raphy and Editing (INT-WICED). Edmonton, AB, Canada: http://ceur-ws.org.
- Newman, P.; and Liu, Y. 2022. Generating Descriptive and Rules-Adhering Spells for Dungeons & Dragons Fifth Edition. In Proceedings of the 9th Workshop on Games and Natural Language Processing within the 13th Language Resources and Evaluation Conference, 54-60. Marseille, France: European Language Resources Association.
- Parry, W. T.; and Hacker, E. A. 1991. Aristotelian logic. Albany, NY: State University of New York Press. ISBN 9780791406892.
- Yang, D.; Zhou, Y.; Zhang, Z.; Jia, T.; Li, J.; and Lc, R. 2022. AI as an Active Writer: Interaction strategies with generated text in human-AI collaborative fiction writing. In Joint Pro- ceedings of the ACM IUI Workshops 2022. Helsinki, Fin- land.
Cited by
Sorted by citations
A survey on large language model based autonomous agents
Wang, L., Ma, C., Feng, X., Zhang, Z., Yang, H., Zhang, J., Chen, Z., Tang, J., Chen, X., Lin, Y., et al. (2024) · Frontiers of Computer Science · doi:10.1007/s11704-024-40231-1 · Cited by 1,941 · see citing works
Unbounded: A Generative Infinite Game of Character Life Simulation
Li, J., Li, Y., Wadhwa, N., Pritch, Y., Jacobs, D. E., Rubinstein, M., Bansal, M., & Ruiz, N. (2024) · arXiv · doi:10.48550/arxiv.2410.18975 · Cited by 2 · see citing works
Memory in the Age of AI Agents
Hu, Y., Liu, S., Yue, Y., Zhang, G., Liu, B., Zhu, F., Lin, J., Guo, H., Dou, S., Xi, Z., et al. (2025) · arXiv · doi:10.48550/arxiv.2512.13564 · Cited by 1 · see citing works
- Authors
- Zhu, A., Martin, L., Head, A., & Callison-Burch, C.
- Affiliations
- University of Pennsylvania (US)
- University of Maryland, Baltimore County (US)
- Venue
- Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment
- Published
- 2023-10-06
- Volume
- 19
- Issue
- 1
- Pages
- 380-390
- ISSN
- 2326-909X (ISSN-L)
- 2334-0924
- OpenAlex
- W4387394580
- Cited by
- 31
- References
- 23
- Citations by year
- 2026: 9 · 2025: 12 · 2024: 9 · 2023: 1
- FWCI
- 5.49
- Type
- conference paper
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment (publishedVersion)
- Funders
- National Science Foundation (2030859)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Artificial Intelligence in Games
- Physical Sciences › Computer Science › Artificial Intelligence › Artificial Intelligence Applications
- Social Sciences › Sociology and Political Science › Digital Games and Media
- Keywords
- large language models, Dungeons & Dragons, tabletop gaming, Calypso, narrative consistency, brainstorming, creative agency
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
