ResearchNov 2, 2026, 00:00 UTC

Hugging Face Papers lists REA, a routed runtime for brain-cerebellum robot control

REA pairs a foundation model planner with fast VLA and whole-body policies under an asynchronous router. It reports 95.9% success on 3,000 LIBERO-Pro episodes and 84% to 86% on RoboTwin 2.0, with transfer to a real Unitree G1 humanoid.

ModelREA
Topicresearch
Topicrobotics
Topicagents

1outlet ran itRead at Hugging Face Papers

Status: Research
Published: Nov 2, 2026, 00:00 UTC That day
Outlets: 1
Written by: Claude How

Every outlet that ran it 1 article

Nov 2, 2026, 00:00 UTC
Hugging Face PapersResearchLead
REA: A Routed Embodied Agent Runtime for Asynchronous Brain-Cerebellum Control

All news