NVIDIA opens ASPIRE, a robotics agent that stores skills as code

NVIDIA researcher Jim Fan announced ASPIRE v1.0 on October 16 in a thread on X, an agentic robotics framework from NVIDIA Research's Generalist Embodied Agent Research group that refines robot-control programs and stores successful ones as reusable skills, with reported benchmark results reaching 99%. The system places a reusable software layer between general-purpose AI models and robot hardware, though performance still depends on the model, benchmark conditions and safeguards around generated code.

NVIDIA opens ASPIRE, a robotics agent that stores skills as code Jim Fan's team says the system can refine robot-control programs and reuse successful skills, with reported benchmark results reaching 99%. By Ryan Merket https://runtimewire.com/author/ryan-merket · Published Primary source: X https://x.com/DrJimFan/status/2111128797181567466 Why it matters ASPIRE puts a reusable software layer between general-purpose AI models and robot hardware: successful control programs can accumulate as skills, while performance still depends on the model, benchmark conditions and safeguards around generated code. NVIDIA researcher Jim Fan @DrJimFan https://x.com/DrJimFan announced ASPIRE v1.0 in an October 16th thread on X https://x.com/DrJimFan/status/2111128797181567466 , releasing an agentic robotics framework built to improve robot behavior by revising programs and saving working skills. The ASPIRE project https://research.nvidia.com/labs/gear/aspire/ is part of NVIDIA Research's Generalist Embodied Agent Research group, not a standalone startup.