Skip to content
Open access

Towards Player-Oriented Procedural Narratives with Stochastic Grammar-Generated Quests

Sep 2026 · Brazilian Symposium on Games and Digital Entertainment · pp. 923-934 · 0 citations · 21 references

TL;DR

This work investigates whether a player-adaptive quest generation method can increase content variability and align generated quests with distinct player behavior profiles, including partial evidence of alignment between generated content and player profiles, although this effect depends on parameter tuning.

Abstract

Introduction: Procedural quest generation has the potential to improve replayability and player engagement, but existing approaches often lack adaptation to different player profiles. Objective: This work investigates whether a player-adaptive quest generation method can increase content variability and align generated quests with distinct player behavior profiles. Methodology: We propose a quest generation system that combines stochastic grammars for structural coherence with Markov-based selection for variability, incorporating player profiling to guide the generation process. The method is evaluated against a random baseline under different parameter configurations. Results: The results of exploratory studies indicate increased diversity and reduced repetition compared to random generation, as well as partial evidence of alignment between generated content and player profiles, although this effect depends on parameter tuning.

Read PDF

Similar papers

Preprint Nov 2026

Towards Self-Evolving Narrative Systems: Real-Time Adaptation and Long-Term Optimization with LLMs

Traditional interactive narrative systems offer strong authorial control and structural coherence but often restrict player agency. In contrast, LLM-driven narratives enable open-ended generation and greater flexibility, yet frequently suffer from inconsistency and diminished narrative control. To navigate this trade-o...

Rui-Sheng Sun, Jia-Qi Shao, Wei-Jia Han et al. · 0 citations
#natural language process... Open access Sep 2026

PERSONAWEAVER: Controllable Diversity Beyond Conventional Archetypes in Procedural Character Generation

PersonaWeaver is introduced, which disentangles world building from behavioral specification and models behavior through setting general, diverse, manually curated banks of moral positions and conversational reactions and allows us to test how far LLM(s) can be pushed beyond their default behavioral patterns across set...

Maan Qraitem, Kate Saenko, Bryan A. Plummer · 0 citations
Open access Sep 2026

Map Generation for Roguelike Games from Textual Descriptions Using Large Language Models

This work proposes an automated system that generates playable and structurally coherent roguelike maps from textual descriptions from textual descriptions using an LLM-driven Assets Generator and a deterministic PCG algorithm for spatial layout generation.

Gustavo Medeiros, Cristiano Bacelar de Oliveira · 0 citations
Preprint Oct 2026

RIGen: Beyond Action Following with Reciprocal Interaction in Generative Gameplay

This work introduces \rig (Reciprocally Interactive Generation), a framework for reciprocal interaction in generative gameplay that combines persistent state and configurable rules, contextual interaction reasoning, and action-conditioned audiovisual generation.

Meng-Fei Li, Yi Zhang, Xingtong Ge et al. · 0 citations
Open access Oct 2026

Toward Ludic-Aware Narrative Generation: A Neuro-Symbolic Framework for Evaluating Playability in LLM-Generated Backstories

Large Language Models produce fluent prose, but for interactive media they tend to generate narratively sterile backstories whose conflicts are all resolved before play begins: the Closure Paradox. Conventional metrics, from n-gram overlap to retrieval-augmented faithfulness, do not reward openness. We propose a dual-a...

L. Peña, José M. Peña, Rubén Buren · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.