Narrative-to-Scene Generation: An LLM-Driven Pipeline for 2D Game Environments
This work addresses the problem of narrative-driven scene generation for procedural content generation in games, offering a scalable prototype for future enhancements.
The paper tackles the challenge of connecting narrative text to playable visual environments by presenting a lightweight pipeline that transforms short narrative prompts into 2D tile-based game scenes, achieving evaluation across ten diverse stories with metrics like tile-object matching and spatial constraint satisfaction.
Recent advances in large language models(LLMs) enable compelling story generation, but connecting narrative text to playable visual environments remains an open challenge in procedural content generation(PCG). We present a lightweight pipeline that transforms short narrative prompts into a sequence of 2D tile-based game scenes, reflecting the temporal structure of stories. Given an LLM-generated narrative, our system identifies three key time frames, extracts spatial predicates in the form of "Object-Relation-Object" triples, and retrieves visual assets using affordance-aware semantic embeddings from the GameTileNet dataset. A layered terrain is generated using Cellular Automata, and objects are placed using spatial rules grounded in the predicate structure. We evaluated our system in ten diverse stories, analyzing tile-object matching, affordance-layer alignment, and spatial constraint satisfaction across frames. This prototype offers a scalable approach to narrative-driven scene generation and lays the foundation for future work on multi-frame continuity, symbolic tracking, and multi-agent coordination in story-centered PCG.