CriticaLLM 框架让 LLM 自动充当桌游主持人，跑完整局 TTRPG
CriticaLLM: Using LLMs as Autonomous Game Master for Tabletop Role-Playing Games
有篇论文做了个全自动 DM，能从编剧情到跑战斗全程带完一局 D&D 那种跑团，还找真人玩家测了 4 个模型，喜欢跑团的可以看看
论文提出 CriticaLLM，一个全自动 Game Master 框架，可运行完整的桌上游角色扮演游戏流程，包括生成剧情、管理探索与战斗阶段。作者先梳理了 LLM 做 TTRPG 主持人需要具备的关键能力，如讲故事、守规则和给玩家行动自由。团队邀请真实 TTRPG 玩家参与评估，并在 4 个不同规模的 LLM 上对比生成剧情和反派的多样性。结果显示该框架适合完整跑一局 TTRPG。
CriticaLLM: Using LLMs as Autonomous Game Master for Tabletop Role-Playing Games
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.
