NVIDIA's ENPIRE lets coding agents self-improve robot policies in the real world, hitting 99% success
chris_j_paxton · x · 2026-10-05
NVIDIA, together with CMU and UC Berkeley, released ENPIRE, a harness framework that lets coding agents autonomously improve robot policies in the real world.
- Key idea: the missing abstraction for automating robotics research is a repeatable real-world feedback loop — reset the scene, execute the policy, verify the outcome, refine the next iteration.
- Four modules: Environment (auto reset & verification), Policy Improvement, Rollout (single or multiple physical robots in parallel), and Evolution (agents analyze logs, consult literature, and improve training infrastructure and algorithm code).
- Headline result: frontier coding agents autonomously develop policies achieving a 99% success rate on challenging real-world dexterous manipulation tasks.
Commenters note the deeper question: what does robotics look like when frontier models can write their own robot code with real-world experimentation?
More from Embodied
- Panasonic building its own humanoid robot, targeting 2029 production in its own factories — CyberRobooo · 2026-10-05
- FailBank Turns Runtime Shield Feedback into Persistent VLA Policy Gains (+25.4 Points Success) — notredame · 2026-10-05
- Reka releases Rho-1 research preview: a 19B omni model unifying text, images, video and robot actions — RekaAILabs · 2026-10-05
- Sensori demos humanoid Yuri: natural voice chat plus VR and exoskeleton teleoperation — YuXiang_IRVL · 2026-10-05
- UniWAM unifies world model and action policy, hits SOTA on LIBERO and RoboTwin benchmarks — LexiLove · 2026-10-05
- EyeRobot 2.0: active gaze lifts robot success from 52% to 67% — no wrist cameras needed — stepjamUK · 2026-10-05