DeepMind and Anthropic Explore Embodied Reasoning: General Models Still Can't Drive Robots Alone
RanjayKrishna · x · 2026-08-01
Recent developments from Google DeepMind and Anthropic have sparked discussions on whether reasoning models can directly decide a robot's whole-body movements. DeepMind's Gemini Robotics 2 layers an embodied reasoning model atop a VLA for whole-body control, while Anthropic has tested general-purpose reasoning models at various control levels.
The consensus is clear: general-purpose reasoning models still cannot control humanoids independently and require a pretrained policy underneath. However, researchers believe that strong multimodal and reasoning capabilities could eventually make this a reality.
To explore this, researchers introduced HumanCLAW. The work decouples 'Action Intelligence' from motor control to finally measure it, revealing that today’s best models are surprisingly bad at it.
More from Embodied
- Steel Bot Announces Open-Source, Fully Programmable Bipedal Humanoids Made in the USA — arian_ghashghai · 2026-08-01
- Caltech Unveils Human-Inspired Multimodal AI Electronic Skin in Science Advances — yisongyue · 2026-08-01
- Google DeepMind Unveils Gemini Robotics 2 to Power Robots of All Shapes — The Decoder · 2026-08-01
- Berkeley Launches OopsieData: An Open Dataset for Robot Failure Clips — berkeley_ai · 2026-08-01
- Hands-on with Roboresso: The AI-Powered Coffee Robot — aziz4ai · 2026-08-01
- Solo Dev Launches Semi-Humanoid Robotics Startup, Seeks Founding Engineers — neurosp1ke · 2026-08-01