Real-Time World Crafting: Generating Structured Game Behaviors from Natural Language with Large Language Models
This work addresses the challenge of enabling emergent gameplay through natural language programming for game developers, though it is incremental as it builds on existing LLM and game engine techniques.
The paper tackles the problem of safely integrating Large Language Models (LLMs) into game engines to allow players to program behaviors via natural language, resulting in a framework that uses LLMs to translate commands into a constrained Domain-Specific Language (DSL) for runtime configuration, with evaluation showing that larger models better capture creative intent and optimal prompting strategies are task-dependent.
We present a novel architecture for safely integrating Large Language Models (LLMs) into interactive game engines, allowing players to "program" new behaviors using natural language. Our framework mitigates risks by using an LLM to translate commands into a constrained Domain-Specific Language (DSL), which configures a custom Entity-Component-System (ECS) at runtime. We evaluated this system in a 2D spell-crafting game prototype by experimentally assessing models from the Gemini, GPT, and Claude families with various prompting strategies. A validated LLM judge qualitatively rated the outputs, showing that while larger models better captured creative intent, the optimal prompting strategy is task-dependent: Chain-of-Thought improved creative alignment, while few-shot examples were necessary to generate more complex DSL scripts. This work offers a validated LLM-ECS pattern for emergent gameplay and a quantitative performance comparison for developers.