← Back to all news
arXiv AI By Ga\"etan Berlaimont, Justin Vanwichelen, Beno\^it Ronval, H\'el\`ene Verhaeghe

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

Read the original on arXiv AI →

CriticaLLM is a fully automated Game Master framework that uses Large Language Models (LLMs) to run entire tabletop role‑playing games, from story creation to managing exploration and combat. The paper outlines key components LLMs should exhibit for TTRPGs and evaluates the system with real players, examining plot and antagonist diversity across four LLMs of different sizes. The results suggest that CriticaLLM is a promising option for automating TTRPG gameplay.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv AI
Oct 7

GAMEGO: Training Game-Dev Agents with Synthetic Trajectories Anchored in Real-World Assets

GameGo is a framework that converts short game ideas into detailed Product Requirements Documents using industry practices, enabling coding agents to generate complete games from sparse user queries. It employs dynamic compression to keep essential gameplay constraints while allowing design flexibility. The authors built GameGoData with over 55,000 development trajectories and GameGoBench with 124 game queries, training GameGoCoder to outperform baselines and match leading models on gamedev benchmarks.

By Haoyue Yang, Jingyao Li, Zhengfan Wu, Jing Liu, Xuanle Zhao, Kang Liu
llmsagentsbenchmarks
More like this →
arXiv AI
Jun 16

Orchestrated Reality: From Role-Play to Living, Playable Game Worlds -- LLM-Driven World Simulation as a Parameterized-Action POMDP

arXiv:2606. 16014v1 Announce Type: cross Abstract: Many games rely on storytelling combined with systems that track levelling, NPC behaviour, and consequence simulation; bridging tightly-authored narrative with deeply-simulated worlds -- most acute in sandbox and open-world settings -- has been prohibitively expensive.

By Yuhang Huang, Chenmiao Li, Chaowei Fang
llmsagentsreinforcement-learning
More like this →
arXiv Computer Vision
Sep 22

GameHorizon Suite: Multi-Horizon Data and Evaluation in Gameplay

arXiv:2609.25001v1 Announce Type: new Abstract: Modern video games provide a measurable testbed for AI models, combining abilities of visual understanding, instruction decomposition, goal planning, a...

By Yiran Wang, Xingyilang Yin, Junfu Pu, Guangzhi Wang, Kaifeng Li, Mingyu Ouyang, Huiqiang Sun, Lingen Li, Cheng Cheng, Wangbo Yu, Honghao Chen, Xiaodong Cun, Chi-Man Pun, Zhiguo Cao, Ying Shan
benchmarks
More like this →
arXiv AI
Sep 15

The Garden of Forking Paths: Threading Narrative Archetype as a Semantic Signal Through Gameplay Planning

The paper introduces Forking Garden, a branching game generation system that threads narrative archetype as a persistent semantic signal throughout the generation pipeline. Narrative progression is modeled with soft Rise/Fall states, guiding the creation of plot nodes, structural constraints, encounter composition, objectives, rewards, and difficulty adaptation. Experiments across ten storylines show that the system produces distinct archetypal trajectories, improves entity diversity, and that Rise/Fall distinctions remain meaningful during play, aiding both narrative understanding and creator interpretation.

By Yunge Wen, Chenliang Huang, Hangyu Zhou, Zhuo Zeng, Yuxuan Weng, Timothy Merino, Julian Togelius, Max Kreminski, Sam Earle
agents
More like this →