Paper page - GameWAM: A World Action Model for Video Games

Source: https://huggingface.co/papers/2608.26200

Abstract

GameWAM is a unified world-action model for native video-game control that jointly predicts future visuals and executable keyboard-mouse actions using block-causal flow matching, mode-specific distributions, and block-cycle replanning.

Modern video games combine first-person perception, rapid visual changes, persistent world state, and heterogeneous native controls. Existing game agents map visual and task context directly to actions but lack explicit world dynamics modeling, whereas interactive game world models predict visual futures from supplied actions but do not serve as task policies.World-Action Models(WAMs) unify these objectives, but remain largely unexplored under the dynamics and open-ended interaction of video games. We introduce GameWAM, to our knowledge the first WAM for native closed-loop gameplay and GUI control. GameWAM jointly generates future visual observations and executable keyboard-mouse trajectories through parallel visual and action generative processes withblock-causal conditioningandflow matching. To support joint world-action learning, we construct synchronized gameplay and GUI trajectories. To handle heterogeneous native control, GameWAM predicts a gameplay/GUI mode at each action step and generates actions withmode-specific prediction distributionsandcontinuous-action normalization. For long-horizon interaction,block-cycle controlpredicts beyond the committed horizon, executes only a short action prefix, and replans from new observations, while fine-grained within-cycle context and hierarchical cross-cycle history preserve temporal continuity. Experiments demonstrate competitive task success with fewer executed native actions than the compared agents. We further uncoverLow-Frequency Action Source Imprinting(LASI), in which low-frequency components of the sampled action source systematically steer coarse generated camera motion under fixed conditioning, revealing a source-sensitivity failure mode ingenerative control. Project page is available at https://yunncheng.github.io/GameWAM/.

View arXiv pageView PDFProject pageGitHub1Add to collection

Get this paper in your agent:

hf papers read 2608\.26200

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

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2608.26200 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2608.26200 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2608.26200 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.