/ Paper arXiv 2611.16009
In short
In shortReport a mistake
Why this ranked
MeasuredPublic numbers, not AIHow ranking works
14 / 100#34 of 1200 papers that day, from GitHub, Hugging Face, Hacker News and Semantic Scholar, looked up the morning it was ranked.
Builder evidence8 / 40
- Code released
Community attention6 / 30
- ▲ 3 upvotes on Hugging Face
Author track record0 / 15
- Nothing found
What the paper shows0 / 15
- Nothing found
Abstract
From the paperThe authors' own words.
GPT-6 Astra can drive a robot arm directly through a fixed harness, and scores of such robot-use agents on RoboDojo have risen quickly since. Reported systems differ in harness and test subset and often change several designs at once, so it is hard to tell which choices produce the gains. We take these designs apart and test them in one framework, along the harness around the model, the action interface, the reuse of experience and the scene geometry given to the model. A lean harness that keeps the full episode history and stops each motion early goes a long way. Reusing experience changes how the model acts but is not a free lunch, and scene geometry helps most, even when depth is predicted from RGB alone. JustRUA starts from the official L3 harness and keeps only what matters most. Even with no learned policy, self-improvement loop or task-specific tuning, this simple harness raises the score on the RoboDojo simulation benchmark substantially, from 29.7 to 50.3.
From the full paper
From the paperCopied from the paper itself by our code.
Reading the paper on arXiv…
Try it
Code, models and demos that use this paper.
- Demos:
- ZefanW/robodojo-replay-explorer ↗1 demo on Hugging Face
- Datasets:
- ZefanW/robodojo-devset-replays ↗1 dataset on Hugging Face
Ask this paper
/ Ask a questionAnswers come from the full paper and name the section
/ Your notes
Select text in the abstract to highlight it or add a note. They stay in this browser.
