StatePlay: State-Aware Game World Models for Mechanics-Consistent Generation

Hugging Face Daily Papers Papers
game-world-models state-aware mechanics-consistent video-generation transformer multi-modal

Summary

StatePlay proposes a state-aware game world model that jointly predicts visual content and game states to generate mechanics-consistent game rollouts, achieving 18.6% improvement in mechanics fidelity.

Recent game world models can generate visually realistic and interactive environments conditioned on player actions. However, games are not defined by pixels alone; they are governed by explicit mechanics, namely state-dependent rules that control health reduction, skill activation, and game termination. These mechanics depend on precise internal states, such as health points, skill meters, and timers, which are tightly coupled with visual observations and determine how gameplay evolves. Without modeling these state dynamics, existing game world models may generate visually plausible rollouts but violate the underlying game rules. In this paper, we propose StatePlay, a novel state-aware game world model that jointly predicts visual content and game states to promote mechanics-consistent generation. StatePlay adopts a mixture-of-transformers (MoT)-style architecture that preserves specialized visual and state representations while enabling cross-modal interaction, allowing predicted states to guide frame generation. Each branch is further optimized with a distinct objective suited to its modality. Experiments show that StatePlay achieves an average normalized L1 distance below 0.06 for state prediction. Furthermore, compared with models without explicit state modeling, our method improves mechanics fidelity in generated game rollouts by 18.6%. Overall, our work highlights the importance of state-aware game world modeling and advances beyond pixel-level realism toward complete and mechanically faithful game generation.
Original Article
View Cached Full Text

Cached at: 07/30/26, 09:47 AM

Paper page - StatePlay: State-Aware Game World Models for Mechanics-Consistent Generation

Source: https://huggingface.co/papers/2607.26754

Abstract

Recentgameworldmodelscangeneratevisuallyrealisticandinteractiveenvironmentsconditionedonplayeractions.However,gamesarenotdefinedbypixelsalone;theyaregovernedbyexplicitmechanics,namelystate-dependentrulesthatcontrolhealthreduction,skillactivation,andgametermination.Thesemechanicsdependonpreciseinternalstates,suchashealthpoints,skillmeters,andtimers,whicharetightlycoupledwithvisualobservationsanddeterminehowgameplayevolves.Withoutmodelingthesestatedynamics,existinggameworldmodelsmaygeneratevisuallyplausiblerolloutsbutviolatetheunderlyinggamerules.Inthispaper,weproposeStatePlay,anovelstate-awaregameworldmodelthatjointlypredictsvisualcontentandgamestatestopromotemechanics-consistentgeneration.StatePlayadoptsamixture-of-transformers(MoT)-stylearchitecturethatpreservesspecializedvisualandstaterepresentationswhileenablingcross-modalinteraction,allowingpredictedstatestoguideframegeneration.Eachbranchisfurtheroptimizedwithadistinctobjectivesuitedtoitsmodality.ExperimentsshowthatStatePlayachievesanaveragenormalizedL1distancebelow0.06forstateprediction.Furthermore,comparedwithmodelswithoutexplicitstatemodeling,ourmethodimprovesmechanicsfidelityingeneratedgamerolloutsby18.6%.Overall,ourworkhighlightstheimportanceofstate-awaregameworldmodelingandadvancesbeyondpixel-levelrealismtowardcompleteandmechanicallyfaithfulgamegeneration.

View arXiv pageView PDFProject pageGitHub1Add to collection

Get this paper in your agent:

hf papers read 2607\.26754

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper1

#### onepiece1999/StatePlay Image-to-Video• Updated20 minutes ago • 2

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2607.26754 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2607.26754 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

State World Models: Execute the Rules, Generate the Pixels

Hugging Face Daily Papers

The paper introduces Stateful Harness, a framework that separates rule-based world state updates from frozen video rendering to improve consistency in interactive world models with hidden state, and evaluates it with the WorldState-Bench benchmark, where the full harness raises rule-compliance from 32% to 92%.

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

Hugging Face Daily Papers

This paper rethinks interactive world models as game engines by examining four key dimensions—action control, state dynamics, state-observation persistence, and real-time generation—and introduces a scalable data engine for Black Myth: Wukong with over 90 hours of gameplay data to advance state-aware game world modeling.

PlayWorld: Benchmarking World Models with Agent Players over Long-Horizon Objectives

Hugging Face Daily Papers

PlayWorld is a benchmark for evaluating interactive video world models using multi-modal agent players pursuing long-horizon objectives. It assesses geometry consistency, interaction fidelity, and state evolution, revealing that current models struggle with spatial consistency and persistent state evolution.

MASS: Multiplayer World Models with Authoritative Shared State

Hugging Face Daily Papers

This paper introduces MASS, a method for multiplayer world models that disentangles world dynamics from view rendering using an authoritative shared state, enabling scalable and consistent multi-agent simulation with up to 1,024 concurrent players.