PAYADOR: A Minimalist Approach to Grounding Language Models on Structured Data for Interactive Storytelling and Role-playing Games

2025-04-09

International Conference on Innovative Computing and Cloud Computing

AI Summary

To address the challenge of simultaneously supporting player free-form input and real-time world-state updates in interactive storytelling (IS) and role-playing games (RPGs), this paper proposes a result-oriented minimalist paradigm: rather than relying on predefined action mappings, it directly predicts world-state transitions induced by player inputs. Methodologically, we employ a lightweight structured world representation to enable context-aware grounding of large language models (LLMs), augmented by prompt engineering and light-weight fine-tuning to enhance controllability and interpretability. Our core contribution lies in reframing action representation as outcome prediction—thereby significantly improving narrative coherence and player behavioral freedom. In RPG settings, the approach achieves high-fidelity, low-latency world evolution. The implementation is open-sourced, facilitating rapid adaptation to diverse interactive narrative domains.

Technology Category

• Humans and AI: Game Design — Procedural Content Generation & Storytelling
• Machine Learning: Large Multimodal Models (LMMs)
• Multiagent Systems: Adversarial Agents

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Every time an Interactive Storytelling (IS) system gets a player input, it is facing the world-update problem. Classical approaches to this problem consist in mapping that input to known preprogrammed actions, what can severely constrain the free will of the player. When the expected experience has a strong focus on improvisation, like in Role-playing Games (RPGs), this problem is critical. In this paper we present PAYADOR, a different approach that focuses on predicting the outcomes of the actions instead of representing the actions themselves. To implement this approach, we ground a Large Language Model to a minimal representation of the fictional world, obtaining promising results. We make this contribution open-source, so it can be adapted and used for other related research on unleashing the co-creativity power of RPGs.

Problem

• Grounding language models on structured data for interactive storytelling
• Predicting action outcomes instead of representing actions in RPGs
• Enhancing player free will and improvisation in role-playing games

Innovation

• Predicts action outcomes, not actions themselves
• Grounds language model on minimal world representation
• Open-source for RPG co-creativity research