Scaling Behavior Foundation Models for Humanoid Robots

Jul 17, 2026

A new arXiv preprint presents a scaling recipe for Behavior Foundation Models (BFMs) in humanoid robot control. The authors coordinate motion tracking learning, on-policy rollouts with diverse reference motions, and a Humanoid Transformer architecture to improve control fidelity and generalization. Their approach achieves substantial reductions in Mean Per-Keypoint Position Error—over 10% in local mode and 82% in global mode—compared to existing humanoid controllers, as demonstrated in both simulation and real-world tests.

Why it matters: This work offers a principled and effective framework for scaling BFMs, advancing the development of more capable and general-purpose humanoid robots.

Full story at: arXiv Robotics ↗