Sign inGet started
Paper · arXiv

From World-Gen to Quest-Line: A Dependency-Driven Prompt Pipeline for Coherent RPG Generation

Large Language Models (LLMs) have shown strong potential for narrative generation, but their use in complex, multi-layered role-playing game (RPG) worlds is still limited by issues of coherence, controllability, and structural consistency. This paper explores a dependency-aware, multi-stage prompt pipeline for procedural RPG content generation that models narrative dependencies through structured intermediate representations. The approach decomposes generation into sequential stages: world building, non-player character creation, player character creation, campaign-level quest planning, and quest expansion. Each stage conditions on structured JSON outputs from previous stages. By enforcin...

AuthorsDominik Borawski, Marta Szulc, Robert Chudy et al.
Primary categorycs.CL
Published28 April 2026
Last updated at source28 April 2026
cs.CLcs.AI
Embed this entry
<iframe src="https://silytics.si/embed/item/dfe592d6-f1d5-40af-ab8b-3abb02c90534" width="420" height="190" style="border:0" loading="lazy" title="Silytics entry"></iframe>

Free, no tracking. More about feeds and embeds.

Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.