Paper page - World Action Models: The Next Frontier in Embodied AI

Source: https://huggingface.co/papers/2605.12090 Authors:

,

,

,

,

,

,

,

,

,

,

,

Abstract

World Action Models unify predictive state modeling with action generation for embodied policy learning, forming a cohesive framework for understanding environment dynamics and action prediction.

Vision-Language-Action (VLA) models have achieved strong semantic generalization forembodied policy learning, yet they learn reactive observation-to-action mappings without explicitly modeling how the physical world evolves under intervention. A growing body of work addresses this limitation by integrating world models, predictive models of environment dynamics, into theaction generationpipeline. We term this emerging paradigmWorld Action Models(WAMs): embodied foundation models that unifypredictive state modelingwithaction generation, targeting a joint distribution over future states and actions rather than actions alone. However, the literature remains fragmented across architectures, learning objectives, and application scenarios, lacking a unified conceptual framework. We formally define WAMs and disambiguate them from related concepts, and trace the foundations and early integration of VLA and world model research that gave rise to this paradigm. We organize existing methods into a structured taxonomy of Cascaded and Joint WAMs, with further subdivision by generation modality, conditioning mechanism, and action decoding strategy. We systematically analyze the data ecosystem fueling WAMs development, spanning robot teleoperation, portable human demonstrations, simulation, and internet-scale egocentric video, and synthesize emerging evaluation protocols organized aroundvisual fidelity,physical commonsense, andaction plausibility. Overall, this survey provides the first systematic account of the WAMs landscape, clarifies key architectural paradigms and their trade-offs, and identifies open challenges and future opportunities for this rapidly evolving field.

View arXiv pageView PDFProject pageGitHub36Add to collection

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2605.12090 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2605.12090 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2605.12090 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.