@DrJimFan: We are open-sourcing V1.0 of our agentic robotics framework, ASPIRE, with full real robot skill discovery and self impr…
Summary
Jim Fan's team open-sources V1.0 of ASPIRE, an agentic robotics framework with real robot skill discovery and self-improvement, noting frontier models like Astra, Opus 5.5, and Sonnet 5.5 have saturated their robot benchmarks.
View Cached Full Text
Cached at: 10/17/26, 11:03 PM
We are open-sourcing V1.0 of our agentic robotics framework, ASPIRE, with full real robot skill discovery and self improvement capabilities! On the day Astra arrived, our lab switched the backend model and saturated all the benchmarks to ~99% over night.
And the frontier is already on the move:
- Opus 5.5 slightly edges out Astra on our robot simulation bench.
- Sonnet 5.5 hits the Pareto frontier of cost vs. robot capability, $12/task.
We first introduced ASPIRE and /robot skill library in June, way before the big models could reliably do robotics. A rising frontier tide lifts all boats, but Astra was a 0->1 tsunami on many tasks.
Now you can also feel the Physical Bitter Lesson at home like we did on that fateful day ;)
links in thread
ASPIRE website: https://research.nvidia.com/labs/gear/aspire/… Open-source codebase: https://github.com/nvlabs/aspire
Guanzhi’s deep dive thread:
Every day is Christmas from now on ;)
On todo list!
This is a deceptively profound post. @DrJimFan thanks for sharing openly.
@DrJimFan I really want to learn. How can I become like you
Similar Articles
@DrJimFan: Today, we give robots a /skills library that self-evolves and compounds indefinitely! Introducing ASPIRE: a robot solvi…
Introducing ASPIRE, a framework for robots to continuously evolve a library of skills through evolutionary search and distillation, enabling efficient sim-to-real and cross-embodiment transfer with up to 10x reduction in transfer learning tokens. The full stack is open-sourced.
ASPIRE: Agentic /Skills Discovery for Robotics
ASPIRE is a continual learning system that autonomously develops and refines robot control programs through iterative exploration, achieving significant improvements in manipulation and household tasks while enabling sim-to-real transfer.
NVIDIA ASPIRE enables robots to accumulate knowledge from successful experiences and reuse it for new tasks, creating a persistent library of skills that improves learning over time
NVIDIA's ASPIRE framework enables robots to build a persistent library of skills from successful experiences, allowing reuse for new tasks and improving learning efficiency over time.
@DrJimFan: I promise this will be the best 20 min you spend today! Robotics: Endgame, the sequel to my last year's Sequoia AI Asce…
In his talk at Sequoia AI Ascent, Dr. Jim Fan presents a roadmap for achieving Physical AGI parallel to LLM success, introducing concepts like video world models, World Action Models (WAM), and the Dexterity Scaling Law, and sharing predictions for the near future.
@seclink: 5. Open-Source Acceleration of Robot World Models - NVIDIA Cosmos 3 + Isaac GR00T: Physical AI Foundation Models - AGIBOT Genie Sim 3.0: The First Fully Open-Source Robot Simulation Platform (Complete Open Source of Code, Data, and Assets) - VLA (Vision-…
Robot world models and simulation platforms are experiencing open-source acceleration: NVIDIA launched Cosmos 3 and Isaac GR00T physical AI foundation models, AGIBOT released Genie Sim 3.0, a fully open-source simulation platform, VLA models become mainstream for manipulation policies, collectively lowering the entry barrier for the robotics field.