Claude Code · Alibaba · Nvidia · Claude · Codex · AI Agent · Decrypt
Nvidia Assembled Robots That Teach Themselves Tapping AI Coding Agents
Compiled by KHAO Editorial — aggregated from 1 source. See llms.txt for citation guidance.
★ Tier-1 Source
A fleet of eight robot arms at Nvidia's GEAR lab spent the past few weeks teaching themselves to insert pins, seat graphics cards, and cut zip ties.
Key facts
- Introducing ENPIRE: they give 8 Codex agents a fleet of robots, an allocation of GPUs, and generous token budget
- The skill came from ENPIRE, a framework detailed in a paper published Tuesday by researchers at Nvidia, Carnegie Mellon University, and UC Berkeley
- Across the four real-world tasks tested, the agents drove their policies to a 99% success rate, according to the paper
- ENPIRE extends an idea Nvidia first floated with Eureka, a 2023 system that used a language model to write reward functions for robots inside a simulator instead of having human engineers do it
Summary
Nvidia, Carnegie Mellon, and UC Berkeley have released ENPIRE, a framework that lets AI coding agents run the full loop of teaching robots new skills with no human supervision. Agents running Codex, Claude Code, and Kimi Code pushed an eight-robot fleet to a 99% success rate on tasks including pin insertion, GPU insertion, and zip-tie cutting. Scaling from one robot to eight cut the time needed to master a task by more than half, though the token bill grew even faster than the time saved. The skill came from ENPIRE, a framework detailed in a paper published Tuesday by researchers at Nvidia, Carnegie Mellon University, and UC Berkeley.