# AW-0: An Embodied World Action Model Framework Unifying Code-Based Planning and Video-Action Prediction

- Source: arXiv cs.RO
- Published: 2026-10-22T04:00:00.000Z
- RoboHot: https://robohot.news/en/items/k9hipd4fdib7xel2c20o8ksxt
- Original: https://arxiv.org/abs/2610.30136

## Summary

The paper proposes AW-0, an agentic world action model framework that combines code-based planning with joint video and action prediction. Within a unified mixture-of-transformers architecture, it simultaneously models three coupled generative streams: code, future video, and robot actions. A code expert generates parameterized skill routines and control logic, while video and action experts generate future visual states and low-level motor commands.