From World Action Models to Embodied Brains: A Roadmap for Open-World Physical Intelligence
Artificial general intelligence ultimately requires agents that can reason and act in the physical world. Action models, vision-language-action policies, and world models have advanced this goal, while World Action Models (WAMs) are particularly promising because they connect candidate interventions with predicted consequences. However, progress remains fragmented: models use incompatible action spaces and prediction targets, datasets and tasks follow different conventions, and runtime systems expose limited interfaces for reuse and evaluation. We review the evolution toward WAMs and organize
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 56%xlang-ai/OSWorld →
- PossiblePossibly related (embedding) · 50%alez007/modelship →
- LinkedLinked via arxiv author · 85%Yuanzhi Liang →
“From World Action Models to Embodied Brains: A Roadmap for Open-World Physical Intelligence”
- LinkedLinked via arxiv author · 85%Xufeng Zhan →
“From World Action Models to Embodied Brains: A Roadmap for Open-World Physical Intelligence”
- LinkedLinked via arxiv author · 85%Haibin Huang →
“From World Action Models to Embodied Brains: A Roadmap for Open-World Physical Intelligence”
- LinkedLinked via arxiv author · 85%Chi Zhang →
“From World Action Models to Embodied Brains: A Roadmap for Open-World Physical Intelligence”
- LinkedLinked via arxiv author · 85%Xuelong Li →
“From World Action Models to Embodied Brains: A Roadmap for Open-World Physical Intelligence”