Introducing Physical Agent 🥚🦾
We post-trained an open 4B general-purpose agent to control a robot, on four GPUs. Weights are open.
It acts by writing tool calls, not an action head. So it is still a general agent, and it learns new robot tasks from one demo in context.
🧵
Excited to share that FINGR won Best Paper at the CoRL 2026 Dexterous Manipulation Workshop! 🏆
Huge thanks to my collaborators @QuanquanPeng03@mattkiim6@xiaolonw and the workshop organizers! It’s been so rewarding to bring my speedcubing hobby into robotics!
Find it. Reach it. Grasp it. Easy for us, hard for a humanoid.
Introducing HuG (#CoRL2026): Learning Humanoid Whole-Body Affordance-Aware Grasping with Active Perception.
The robot looks around for a half-hidden object, squats or stretches its whole body to reach it, and grasps. Zero real demos, zero-shot to unseen objects and everyday scenes, from low tables to high shelves.
🌐 https://t.co/XQ8SDmZf97
Find it. Reach it. Grasp it. Easy for us, hard for a humanoid.
Introducing HuG (#CoRL2026): Learning Humanoid Whole-Body Affordance-Aware Grasping with Active Perception.
The robot looks around for a half-hidden object, squats or stretches its whole body to reach it, and grasps. Zero real demos, zero-shot to unseen objects and everyday scenes, from low tables to high shelves.
🌐 https://t.co/XQ8SDmZf97
Excited to see OpenRoboKit released! 🚀 Jianglong has always been committed to making robotics more accessible to the broader community, and this project reflects that vision. A great step toward more efficient robotics development.
Glad to have contributed to RetargetingKit.
Excited to share OpenRoboKit, our series of open-source robotics projects! 🤖
- RoboKit for fast, scalable optimization & simulation https://t.co/9KosQmzZP3
Our RoboKit paper has been accepted for a spotlight at #CORL2026
- RetargetingKit for motion transfer & teleoperation https://t.co/fniCD3Uhms
- GraspKit for end-to-end grasping https://t.co/Tikg9Fz94U
Website: https://t.co/fzDLfxoPh5
Check the video (sound on 🎵) for a 16-hour grasping time-lapse in beautiful San Diego, plus a quick look at dexterous retargeting and robot simulation.
Excited to share OpenRoboKit, our series of open-source robotics projects! 🤖
- RoboKit for fast, scalable optimization & simulation https://t.co/9KosQmzZP3
Our RoboKit paper has been accepted for a spotlight at #CORL2026
- RetargetingKit for motion transfer & teleoperation https://t.co/fniCD3Uhms
- GraspKit for end-to-end grasping https://t.co/Tikg9Fz94U
Website: https://t.co/fzDLfxoPh5
Check the video (sound on 🎵) for a 16-hour grasping time-lapse in beautiful San Diego, plus a quick look at dexterous retargeting and robot simulation.
It turns out that with a minimal set of tools and workflows, agents can generate super cool motion for animation characters 💃 and humanoid robots 🤖, even with hand-object interaction!
Given text, images, or videos, the agent selects motion models, builds the scene and object, retargets to the character or robot, and refines poses, timing, and contacts from rendered feedback.
Try our motion generation skill in RoboSkills! https://t.co/4CTaKgAZUX We also provide a fixed agent-free workflow for motion without interaction.
We introduce RoboSkills: a minimal, low-cost skillset for agentic robotics 🤖
It supports diverse robotics workflows, such as learning cat’s cradle 🧶 from a human video (Real2Sim) and transferring multi-person motion to characters and humanoids 💃 (Motion Generation).
We also support Auto Research, Agent as Policy, and Agentic Simulation. With suitable tools and workflows, we enable cheaper models to solve complex tasks.
GitHub: https://t.co/pofI0n6xoM
Website: https://t.co/qxzU18vN0R
Watch the video for more examples.
We introduce RoboSkills: a minimal, low-cost skillset for agentic robotics 🤖
It supports diverse robotics workflows, such as learning cat’s cradle 🧶 from a human video (Real2Sim) and transferring multi-person motion to characters and humanoids 💃 (Motion Generation).
We also support Auto Research, Agent as Policy, and Agentic Simulation. With suitable tools and workflows, we enable cheaper models to solve complex tasks.
GitHub: https://t.co/pofI0n6xoM
Website: https://t.co/qxzU18vN0R
Watch the video for more examples.
Humanoids today mostly manipulate objects with their hands. As humans, we use much more than our hands: we brace boxes against our chests, tuck objects under our arms, and roll balls along our forearms.
Introducing Whole-Body Dexterity (WBD), turning the humanoid body into one large dexterous manipulator.
https://t.co/qXGSMtrAXp 🧵👇
Can we make dexterous robots compliant without sacrificing precise control?
Excited to introduce FOMO-Dex: Force-Modulated Dexterity! 🖐️
FOMO-Dex brings force-aware compliance to dexterous teleoperation, enabling robots to pick up thin cards and chips 🃏, cut paper 🔪, turn nuts 🔩, and use screwdrivers 🪛.
These force-aware demonstrations also train better autonomous policies!
🎥 Videos & paper: https://t.co/SC3bdKXOai
🧵👇 (1/8)
Our G1 robot found its way to the pantry, picked up a Pringles can, and handed it over. No pre-built map. No training for this task.
Behind it is a coding agent, writing, running, and fixing the robot's programs as it goes. And it self-evolves: what works is saved as code for the next task, no retraining needed. This is ASENA.
Joint work with @Isabella__Liu, @edmund_bu, Johan Bjorck, @yin_hongxu, @zhengyiluo, @jankautz, @DrJimFan, @yukez, and @Sifei30488L. 🧵👇
Can we scale robot learning without scaling human labor? 📈
Demonstrations, resets, failure recovery, constant supervision—collecting robot data still takes substantial human effort.
🔑 Three keys let agents take on more of the work:
1. Real2Sim2Real: Agents explore and learn in digital twins, where trial and error is safer and cheaper.
2. Autonomous Recovery: Robots learn to recover from unexpected failures instead of waiting for human resets.
3. Human-on-Demand Learning: Multiple robots run in parallel, and humans step in only when autonomous recovery falls short.
🥑 Recova brings these together to get more robot learning out of every hour of human effort.
https://t.co/Wy7gucGq9r
Joint work with @anjjei, Johan Bjorck, @ZhidingYu, @yin_hongxu, @jankautz, @DrJimFan, @yukez, and @Sifei30488L.
👇 Here's how it works 🧵
Yutong’s been a hardcore speedcuber for years. FINGR finally makes his dream real — a dexterous hand that solves the 2×2 with continuous finger tricks just like a human. Truly impressive work. Highly recommend!
Astra is already helping us tune complex dexterous manipulation algorithms. Excited to see how far we can push it toward discovering more reusable manipulation primitives and transferable skills.
Evolving dexterity with GPT-6 Astra 🖐️
Been trying Astra recently. Its zero-shot dexterous manipulation is already quite surprising. More interesting is seeing it learn and improve through simulation training, from pen spinning and Rubik's Cube to hammer use.
The real goal would be to evolve this dexterity in the real world.
https://t.co/GZjQTsklYc
We’re sharing a solution to the Navier-Stokes Millennium Prize Problem, one of the deepest problems at the frontier of mathematics.
The proof was produced by a group of agents, using an OpenAI next-generation model significantly more capable than GPT-6 Astra.
The problem concerns whether the description of smooth three-dimensional fluid motion modeled by the Navier-Stokes equations can break down. It has remained unresolved for roughly 90 years.