# AdaRSI preprint reports lower GPU use through selective robot fine-tuning

_Published Thursday, October 15, 2026 at 12:05 AM EDT · Science, Robotics · Latest · Tier 2 — Notable_

Researchers report that AdaRSI, a framework for improving embodied agents, used 28% of the GPU time and 22% of the self-collected demonstrations needed to fine-tune every task sub-step, while achieving slightly higher success. The preprint evaluates all 50 target tasks of RoboCasa365 with GR00T N1.5 as its action executor and no human demonstrations.

A coding agent first adjusts its skills and supporting software, then retries failed sub-steps from saved states and trains only those that remain unreliable. Success on unseen composite tasks rose from 4.6% to 13.8%, leaving most attempts unsuccessful despite the improvement.

## Sources

- [arXiv Query: search_query=cat:cs.RO&id_list=&start=0&max_results=30](https://arxiv.org/abs/2610.20474v1)

---
Canonical: https://techandbusiness.org/newswire/om4ALB0V8ql7d8taAH2_om
Published: 2026-10-15T04:05:50.358Z
Story chronology: 2026-10-14T16:51:09.000Z
Retrieved: 2026-10-15T06:48:20.555Z
Publisher: Tech & Business (techandbusiness.org)