English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

From Pixels to States: Rethinking Interactive World Models as Game Engines

Forum topic · 小凯 · 2026-07-17

Summary

This survey re-frames interactive world modeling for games through the action-state-observation loop used by conventional engines. It argues that next-generation game engines built on video generative models must satisfy four requirements: controllable player actions, dynamic game state evolution, state-observation persistence, and real-time interactive generation. For each dimension, the authors group existing methods into representative families and analyze their trade-offs. As a complementary contribution, the paper introduces a scalable data engine built around Black Myth: Wukong, producing over 90 hours of gameplay with frame-aligned player actions, ground-truth game states, visual observations, and structural and semantic annotations. The resource targets state-aware interactive world modeling. The work aims to clarify the current landscape and accelerate progress toward genuinely interactive, persistent, and real-time game worlds.

Overview

Field: Computer Vision (CV) Authors: Zhen Li, Zian Meng, Shuwei Shi, Mingliang Zhai, Jiaming Tan, Chuanhao Li, Kaipeng Zhang Published: 2026-07-15 arXiv: 2607.14076

English Abstract

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. Using this loop as an organizing perspective, this paper surveys interactive game world modeling along four dimensions: player action control, game state dynamics, state-observation persistence, and real-time interactive generation. For each dimension, the authors start from the capabilities required by interactive game worlds, group existing approaches into representative families, and discuss the strengths and trade-offs of each family. As a complementary analysis, the paper proposes a scalable data engine for *Black Myth: Wukong* that collects over 90 hours of gameplay containing frame-aligned player actions, ground-truth game states, and visual observations, together with structural and semantic annotations, as a resource for state-aware game world modeling. The authors hope the survey offers a clear picture of the field and catalyzes further progress toward interactive game worlds.

*Auto-collected on 2026-07-17*

Tags

#computer-vision#world-models#video-generation#game-engines#interactive-generation#arxiv#survey#benchmark

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/178395198