$ cat wiki/papers/2026/2606.19980-enpire-robot-autoresearch.md
ENPIRE: Agentic Robot Policy Self-Improvement in the Real World
TL;DR
A fleet of 8 real robots autonomously runs its own research loop — reading papers, proposing hypotheses, running physical trials, and rewriting code — with no humans in the loop. Achieves 99% pass@8 on demanding manipulation tasks; discovers a physical scaling law.
Method
ENPIRE (Empirical Neural Policy self-Improvement on Robot Experiments) assigns a frontier LLM-based coding agent to a fleet of 8 real physical robots:
- Read: agent ingests published robotics papers as background context
- Hypothesize: proposes an algorithmic improvement hypothesis
- Reset: agents physically reset experimental scenes (no human help)
- Execute: runs parallel trials across the 8-robot fleet
- Verify: checks results against a binary success criterion
- Rewrite: updates control code based on empirical outcomes
The entire loop is autonomous — no human researchers design experiments, interpret results, or modify code.
Results
- 99% pass@8 on contact-rich manipulation benchmarks: GPU seating into a motherboard socket; tying zip ties with a cutting tool
- Physical scaling law discovered: superlinear speedup with more parallel robots — the first empirical demonstration of a data-parallel scaling law for real-world physical manipulation (analogous to LLM training-data scaling)
- Jim Fan: "AutoResearch in the physical world for the first time"
Significance
ENPIRE closes the research loop that EgoScale (June 7, 2026) opened:
- EgoScale showed dexterous skills can be acquired from 20,000+ hours of human egocentric video
- ENPIRE shows robots can now improve those skills autonomously, without any human-in-the-loop research step
The physical scaling law — parallel robots → superlinear task speedup — is the first evidence that the LLM-era "scale → capability" paradigm transfers to self-improving real-world robot policies, not just initial skill acquisition.
Open Questions
- Does the approach generalize to out-of-distribution, novel tasks?
- What is the minimum fleet size for the superlinear scaling law to hold?
- Will the loop extend to locomotion and multi-robot coordination, or is it manipulation-only?
- How does it interact with safety constraints (physical actuation risk in autonomous loops)?
Cite
Xiao et al. "ENPIRE: Agentic Robot Policy Self-Improvement in the Real World." arXiv:2606.19980, June 2026. https://arxiv.org/abs/2606.19980
Related
- Embodied Agents — broader embodied AI context; see EgoScale entry
- Agentic Reinforcement Learning — agentic RL background
- Jim Fan — senior author; NVIDIA GEAR Lab
- NVIDIA — lab affiliation; Cosmos 3, GR00T