Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A Text-to-Game Engine for UGC-Based Role-Playing Games

Lei Zhang, Xuezheng Peng, Shuyi Yang, Feiyang Wang

TL;DR

The paper tackles the challenge of scaling RPG development for user-generated content by introducing a Generative AI-based text-to-game engine and the Zagii platform. It combines a Game Building Copilot with an AI-native engine featuring PMTA-driven NPCs, emergent real-time narratives, and multi-modal rendering to transform textual prompts into complete RPG experiences. Experimental deployment and data from hundreds of developers and tens of thousands of players demonstrate feasibility and scalability, with 168 published games and over 60k sessions (excluding an outlier). The work highlights potential for democratized, open-ended RPG creation and outlines concrete future directions, including asset generation, engine optimization, and robust AB testing.

Abstract

The transition from professionally generated content (PGC) to user-generated content (UGC) has reshaped various media formats, encompassing formats such as text and video. With rapid advancements in generative AI, a similar transformation is set to redefine the gaming industry, particularly within the domain of role-playing games (RPGs). This paper introduces a novel framework for a text-to-game engine that leverages foundation models to transform simple textual inputs into intricate, multi-modal RPG experiences. The engine dynamically generates game narratives, integrating text, visuals, and mechanics, while adapting characters, environments, and gameplay in realtime based on player interactions. To evaluate and demonstrate the feasibility and versatility of this framework, we developed the 'Zagii' game engine. Zagii has successfully powered hundreds of RPG games across diverse genres and facilitated tens of thousands of online gameplay sessions, showcasing its scalability and adaptability. These results highlight the framework's effectiveness and its potential to foster a more open and democratized approach to game development. Our work underscores the transformative role of generative AI in reshaping the gaming lifecycle and advancing the boundaries of interactive entertainment.

A Text-to-Game Engine for UGC-Based Role-Playing Games

TL;DR

The paper tackles the challenge of scaling RPG development for user-generated content by introducing a Generative AI-based text-to-game engine and the Zagii platform. It combines a Game Building Copilot with an AI-native engine featuring PMTA-driven NPCs, emergent real-time narratives, and multi-modal rendering to transform textual prompts into complete RPG experiences. Experimental deployment and data from hundreds of developers and tens of thousands of players demonstrate feasibility and scalability, with 168 published games and over 60k sessions (excluding an outlier). The work highlights potential for democratized, open-ended RPG creation and outlines concrete future directions, including asset generation, engine optimization, and robust AB testing.

Abstract

The transition from professionally generated content (PGC) to user-generated content (UGC) has reshaped various media formats, encompassing formats such as text and video. With rapid advancements in generative AI, a similar transformation is set to redefine the gaming industry, particularly within the domain of role-playing games (RPGs). This paper introduces a novel framework for a text-to-game engine that leverages foundation models to transform simple textual inputs into intricate, multi-modal RPG experiences. The engine dynamically generates game narratives, integrating text, visuals, and mechanics, while adapting characters, environments, and gameplay in realtime based on player interactions. To evaluate and demonstrate the feasibility and versatility of this framework, we developed the 'Zagii' game engine. Zagii has successfully powered hundreds of RPG games across diverse genres and facilitated tens of thousands of online gameplay sessions, showcasing its scalability and adaptability. These results highlight the framework's effectiveness and its potential to foster a more open and democratized approach to game development. Our work underscores the transformative role of generative AI in reshaping the gaming lifecycle and advancing the boundaries of interactive entertainment.
Paper Structure (21 sections, 9 figures, 1 table)

This paper contains 21 sections, 9 figures, 1 table.

Table of Contents

  1. Introduction
  2. Related Works
  3. Game Building Copilot
  4. AI-Native Game Engine
  5. Role-Playing System
  6. Game Status Manager
  7. Emergent Narrative System
  8. Real-time Narrative Generation
  9. Interactive Narrative Consumption
  10. Multi-Modal Rendering System
  11. Entities
  12. Perception and Retrieval
  13. Adaptive Generation
  14. System Implementation and Experiments
  15. Implementation of the Experiment System
  16. ...and 6 more sections

Figures (9)

  • Figure 1: The game life cycle difference between traditional RPGs and AI-native RPGs
  • Figure 2: The text-to-game structure
  • Figure 3: Multi-agent Game Building Copilot
  • Figure 4: The conceptual architecture of Zagii Engine
  • Figure 5: PMTA framework of Role-playing System
  • ...and 4 more figures