Metraipolis › archive › dc_fcc515c20f20

CriticaLLM: Using LLMs as Autonomous Game Master for Tabletop Role-Playing Games — arXiv:2610.21525

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.21525
License (as archived)
CC0-1.0
Archived
2026-10-16T09:03:37.644Z
SHA-256 of the archived text
e320c0d80cc3a23593a042be43651fbd5741072ad6e6ec869c80cda7d04e30ba
Stable URL of this page
https://metraipolis.com/documento/dc_fcc515c20f20

How to cite

CriticaLLM: Using LLMs as Autonomous Game Master for Tabletop Role-Playing Games — arXiv:2610.21525 — arXiv (en), https://arxiv.org/abs/2610.21525 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fcc515c20f20 (Metraipolis archive dc_fcc515c20f20, sha256 e320c0d80cc3a23593a042be43651fbd5741072ad6e6ec869c80cda7d04e30ba)
BibTeX
@misc{dcfcc515c20f20,
  title = {CriticaLLM: Using LLMs as Autonomous Game Master for Tabletop Role-Playing Games — arXiv:2610.21525},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.21525},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fcc515c20f20; sha256 e320c0d80cc3a23593a042be43651fbd5741072ad6e6ec869c80cda7d04e30ba},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.21525. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large Language Models (LLMs) have shown impressive capabilities across many tasks, including processing large amounts of text, following instructions, and generating ideas. This allows the use of such models in various contexts, including games and Tabletop Role-Playing Games (TTRPGs), such as Dungeons & Dragons. However, these games include many complex components, from crafting interesting stories to adhering to rules, while allowing some freedom in players' actions. In this work, we first highlight key components that LLMs should exhibit in the context of TTRPGs. Then, we introduce our framework, CriticaLLM, a fully automated Game Master that can run entire TTRPG games, from creating diverse and interesting stories to managing exploration and combat phases. We evaluate our framework with actual TTRPG players and examine the diversity of generated plots and antagonists across four LLMs of varying sizes. Overall, our framework appears to be a promising option for running entire TTRPG games.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.21525 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-16T08:44:17.762Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).