An embodied multi-agent framework uses learned correction codes and a vision-language-action model with motion-aware history and latent world modeling to improve robot control, failure recovery, and training efficiency.
Foundation models increasingly guide robot actions, yet sustained autonomy requires efficient control and failure recovery. We introduce A2-MEAS, an embodied multi-agent framework built around code as a scaling interface. Learned correction codes combine corrective language, spatial evidence, execution history, and action proposals. MetaBrain provides training supervision and runtime guidance. A correction encoder and adapter absorb this knowledge into policy weights during training, while fresh codes adapt behavior with frozen weights at deployment. The action model, A2-WLA, adds motion-aware history and a latent world model to a vision-language-action policy. Surprisingly, this simple…
foundation modelsembodied multi-agent frameworkcode as scaling interfacelearned correction codescorrective languagespatial evidenceexecution historyaction proposalsMetaBraintraining supervision
- Upvotes
- 22
- Authors
- 10
- Published
- Nov 6, 2026
Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.