Paper Overview
Research Area: Computer Vision (CV) Authors: Zhen Li, Zian Meng, Shuwei Shi, Mingliang Zhai, Jiaming Tan, Chuanhao Li, Kaipeng Zhang Posted: 2026-07-15 arXiv: 2607.14076
Abstract (English)
Building interactive worlds that respond coherently to player actions has long been a shared goal of computer graphics, games, and artificial intelligence. Recent video generative models provide a data-driven route toward this goal by predicting future observations conditioned on user actions, and are increasingly regarded as potential next-generation game engines. Realizing a genuinely interactive game world, however, requires interaction outcomes that follow rules over evolving game conditions, consequences that persist over long horizons, and a generation loop that operates in real time. Conventional game engines realize these properties through a recurrent action-state-observation loop, in which player actions update an explicit game state according to predefined rules and observations are rendered from the resulting state.
Chinese Summary (translated)
Using this recurrent loop as an organizing perspective, the paper surveys interactive game world modeling across four dimensions:
1. Player action control 2. Game state dynamics 3. State-observation persistence 4. Real-time interactive generation
For each dimension, existing methods are grouped into representative families based on the capabilities required for interactive game worlds, and the advantages and trade-offs of each family are discussed.
Data Contribution
As a complementary analysis, the authors present a scalable data engine built on *Black Myth: Wukong*, collecting over 90 hours of gameplay containing:
- Frame-aligned player actions
- Real game states and visual observations
- Structural and semantic annotations
---
*Auto-collected on 2026-07-17*