Real-Time World Crafting: Generating Structured Game Behaviors from Natural Language with Large Language Models
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915563254579200 |
|---|---|
| author | Drake, Austin Dong, Hang |
| author_facet | Drake, Austin Dong, Hang |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_16952 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Real-Time World Crafting: Generating Structured Game Behaviors from Natural Language with Large Language Models Drake, Austin Dong, Hang Human-Computer Interaction Computation and Language H.5.2; I.2.7 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. |
| title | Real-Time World Crafting: Generating Structured Game Behaviors from Natural Language with Large Language Models |
| topic | Human-Computer Interaction Computation and Language H.5.2; I.2.7 |
| url | https://arxiv.org/abs/2510.16952 |