World Action Models: A Survey

Hugging Face Daily Papers Papers
world-action-models survey embodied-ai predictive-models decision-making action-models

Summary

This survey provides a comprehensive overview of World Action Models (WAMs), predictive-action systems that generate future states for decision-making, and organizes existing works by their required outputs and design choices.

World Action Models (WAMs) are embodied predictive-action models that make a forecast of the future available to action. Recent WAMs repurpose large video generation models, and a parallel line relies on language or vision-language backbones without a video-generation core. This rapid expansion has blurred the boundary among broad world models, video generation models, action-grounded video world models, Vision-Language-Action policies, and WAMs. This survey gives the field a common account. It first clarifies these boundaries, then organizes existing works through two complementary views. The first view asks what each method is required to generate, spanning rendered futures, latent futures, and video-generation-free action reasoning. The second view decomposes each method by predictive substrate, backbone, action coupling, and deployment regime. This anatomy supports a unified discussion of interactability, causality, persistence, physical plausibility, and generalization, followed by data, evaluation, and open challenges. Across these axes, a consistent design pattern emerges: WAMs are not simply video generators with action heads, but predictive-action methods whose design choices trade representational richness against compute, memory, latency, and action-label cost. The field is moving toward methods that generate less of the future while preserving what control requires. The survey homepage is available at https://world-action-models.github.io/.
Original Article
View Cached Full Text

Cached at: 06/23/26, 05:41 AM

Paper page - World Action Models: A Survey

Source: https://huggingface.co/papers/2606.20781

Abstract

World Action Models are predictive-action systems that generate future states for decision-making, with designs balancing representational richness against computational constraints.

World Action Models(WAMs) areembodied predictive-action modelsthat make a forecast of the future available to action. Recent WAMs repurpose largevideo generation models, and a parallel line relies on language orvision-language backboneswithout a video-generation core. This rapid expansion has blurred the boundary among broad world models,video generation models, action-grounded video world models, Vision-Language-Action policies, and WAMs. This survey gives the field a common account. It first clarifies these boundaries, then organizes existing works through two complementary views. The first view asks what each method is required to generate, spanning rendered futures, latent futures, and video-generation-free action reasoning. The second view decomposes each method bypredictive substrate, backbone,action coupling, anddeployment regime. This anatomy supports a unified discussion ofinteractability,causality, persistence,physical plausibility, andgeneralization, followed by data, evaluation, and open challenges. Across these axes, a consistent design pattern emerges: WAMs are not simply video generators with action heads, but predictive-action methods whose design choices trade representational richness against compute, memory, latency, and action-label cost. The field is moving toward methods that generate less of the future while preserving what control requires. The survey homepage is available at https://world-action-models.github.io/.

View arXiv pageView PDFProject pageGitHub217Add to collection

Get this paper in your agent:

hf papers read 2606\.20781

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/2606.20781 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2606.20781 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2606.20781 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

World Action Models: The Next Frontier in Embodied AI

Hugging Face Daily Papers

This survey paper introduces World Action Models (WAMs), a unified framework for embodied AI that integrates predictive state modeling with action generation. It provides a taxonomy of existing methods, analyzes the data ecosystem, and outlines evaluation protocols for this emerging paradigm.

The DAWN of World-Action Interactive Models

Hugging Face Daily Papers

This paper introduces DAWN, a latent generative baseline for World-Action Interactive Models (WAIMs) that jointly models scene evolution and action generation through recursive refinement, achieving strong long-horizon planning in autonomous driving scenarios.

BadWAM: When World-Action Models Dream Right but Act Wrong

Hugging Face Daily Papers

BadWAM introduces a framework for adversarial attacks on World-Action Models (WAMs), breaking the alignment between imagination and action via small visual perturbations. The attacks significantly reduce task success rates, exposing a vulnerability in this class of models.