Fun-Aware Modeling and Narrative Generation Using LLMs for Role-Playing Games
IEEE Access · 2026 · 14 · 102264-102281
DOI: 10.1109/access.2026.3710747 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Access, 2026. Verfasst von Yoones A. Sekhavat und 1 weiteren Autor:innen. Die Arbeit nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Modern College of Business and Science.
Abstract (Originalsprache)
Creating engaging narratives for role-playing games (RPGs) remains a challenge. Traditional handcrafted and branching story systems offer limited adaptability, while large language models (LLMs) typically optimize linguistic quality rather than player enjoyment. To address this gap, this study proposes a fun-aware LLM-based narrative generation framework that treats fun as a dynamic, multi-dimensional signal guiding iterative story generation. The framework evaluates narrative segments using six interpretable features: surprise with coherence, agency density, tension oscillation, narrative payoff ratio, tonal variability, and rule-bending moments. A human-subject study involving 24 participants showed that fun-aware narratives significantly improved perceived enjoyment, player agency, novelty, and replayability compared with baseline LLM-generated narratives while maintaining narrative coherence. Correlation analysis further revealed strong agreement between computational fun estimates and human enjoyment ratings ( $r = 0.71$ ), supporting the validity of the proposed metrics. To further evaluate the framework, 80 paired RPG narratives comprising 944 narrative segments were generated under controlled conditions. Compared with baseline narratives, the fun-aware framework produced higher composite fun scores ( $M = 5.82$ vs. 4.71), greater event novelty ( $M = 6.77$ vs. 4.91), and richer branching structures ( $M = 2.34$ vs. 1.58 choices per segment). These findings suggest that modeling fun as an explicit design objective can improve both player-perceived engagement and computational measures of narrative diversity and interactivity without compromising narrative coherence.
Förderung
- Modern College of Business and Science
Zitieren
APA
Sekhavat, Y. A., & Mani, J. (2026). Fun-Aware Modeling and Narrative Generation Using LLMs for Role-Playing Games. IEEE Access, 14, 102264-102281. https://doi.org/10.1109/access.2026.3710747
Vancouver
Sekhavat YA, Mani J. Fun-Aware Modeling and Narrative Generation Using LLMs for Role-Playing Games. IEEE Access. 2026;14:102264-102281. doi:10.1109/access.2026.3710747
BibTeX
@article{Sekhavat2026,
author = {Sekhavat, Yoones A. and Mani, Joseph},
title = {Fun-Aware Modeling and Narrative Generation Using LLMs for Role-Playing Games},
journal = {IEEE Access},
year = {2026},
volume = {14},
pages = {102264--102281},
doi = {10.1109/access.2026.3710747}
}
EUVIMED