Robots shouldn't need to be fine-tuned for every new task.
Introducing Runtime (YC F26). We're reimagining robot policies: explore in simulation, then act in the real world.
Watch it thread a rope.
No fine-tuning. No teleoperation.
Frontier models like GPT-6 Astra and Gemini Argon 4 can control robots, but how much does the harness around them impact performance?
We used our Nomad-Harness to test Gemini Argon on LIBERO tasks to test if text based skills could help with harder tasks that require more manipulation. We iteratively refined the skill with a critic agent reviewing failed attempts.
Across 20 initial states per task, Argon’s native success rate improved:
• Bowl into drawer: 0/20 → 17/20
• Mug into microwave: 0/20 → 8/20
These results show that reusable text instructions can improve robot control, and they also transfer between models, with improvements also shown for GPT-6-Astra and Fable 5.1 with the same skill.