| title | PhysEvo: Astra Can Act, Let It |
|---|---|
| authors | Wenqing Tian, Zeyu Zhang, Zhaocheng Liu, Fengwei Liu, Qiang Liu, Liang Wang |
| date | 2026-10-06 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2610.08995 |
| upvotes | 33 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf |
| abstract | Astra can act, yet reliable manipulation depends on the system through which it observes and controls the world. We introduce PhysEvo, a framework for physical recursive self-improvement (RSI) around a single frozen model. A task agent executes robot tasks; a meta-agent uses the resulting trajectories to diagnose failures, revise tools and skills, and test corrections. The meta-agent can also improve its own diagnostic tools, so retained revisions support both later action and later self-improvement. This process develops joint-level control, evidence-seeking observation, and reusable manipulation skills without model-weight updates or a separately trained action policy. Across 42 RoboDojo tasks, held-out-layout evaluation of retained task-specific deployment versions yields a five-dimension average score of 68.14/100 and 62.00% success, compared with 47.17% for RoboDawn's one-shot Astra agent, the strongest published reference in our comparison. On eight manipulation tasks challenging direct Astra, PhysEvo achieves 55.00% success, compared with 1.25% for the direct-Astra reference. Deploying the simulation-evolved harness on AgileX PiPER and continuing skill revision yields 90.60/100 average score and 84.00% success across 25 trials on five real-world tasks. PhysEvo turns the consequences of action into persistent, testable changes to how a frozen model acts and improves. |
cite
@misc{tian2026physevo,
title={PhysEvo: Astra Can Act, Let It},
author={Wenqing Tian and Zeyu Zhang and Zhaocheng Liu and Fengwei Liu and Qiang Liu and Liang Wang},
year={2026},
eprint={2610.08995},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2610.08995}
}