Skip to content
NewA calmer, faster ZeroHour

27B reasoning model learns real-robot control from simulation alone

Original title: Training Reasoning Models in Simulation to Natively Use Real Robots

arXiv cs.AI / cs.LG / cs.CLby Jiaming Tang ()1 min read1 · 1 read
Part of a story covered by 2 sourcesSimulation-trained 27B model transfers robot skills to real dual armsMerged summary & timeline
AI summary · x-ai/grok-4.7Summaries by Vani AI

It succeeded in 60% of real dual-arm trials after simulation-only training; the untuned base model succeeded in none.

Researchers trained an open-weight 27B reasoning model with robot-use reinforcement learning entirely in simulation, using a Post-training Engine for Agentic Robotics and no demonstrations. The model outputs the next end-effector pose from observations and chain-of-thought, without a harness. Skills transferred to an unseen robot, the real world and novel instructions. On LIBERO, success rose from 1.6% to 74.4%, near GPT-6 Astra and GPT-6.1 Sol at maximum reasoning effort, with no measured drop on nine general benchmarks.

Key facts
  • After LIBERO and RoboDojo training, real dual-arm trials succeeded 60% of the time.
  • On LIBERO-Pro, the model succeeded in 57.4% of episodes with a new task in a familiar scene.
  • Demonstration-tuned π0.5 succeeded in 0.75% of those LIBERO-Pro episodes.
  • The authors report no measurable degradation on nine reasoning, coding and vision benchmarks.
Explain this AI news with Vani AIWhat was announced, what is new and why it matters, in a new chat

From the original article

1 min read at arxiv.org

Robot-use agents (RUAs) have emerged as a promising approach to general-purpose robot control. However, strong performance has so far been achieved only by frontier proprietary models such as GPT-6 Astra and Claude Fable 5. 2, whereas open-weight models remain substantially less capable.

arXiv cs.AI / cs.LG / cs.CL

By Jiaming Tang · arxiv.org

Read the full article at arXiv cs.AI / cs.LG / cs.CL

A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.