# Robot learning preprint reports gains across multiple manipulation tasks

_Published Wednesday, November 4, 2026 at 12:06 AM EST · Robotics, AI, Science · Latest · Tier 2 — Notable_

Researchers report that SR-DP, a method for training one robot control model across multiple tasks, achieved a 68.4% average success rate on six RoboTwin tasks. In an arXiv preprint, they report gains of 21.8 points over multi-task VO-DP and 3.8 points over the strongest per-task baseline.

The method combines a frozen visual encoder with a training approach that routes updates through separate mathematical components of the control model. It targets interference between incompatible actions when tasks share a model.

On four real-world tasks requiring two robot arms, the second training stage achieved a 43.0% average success rate, improving on the first stage by 19.0 points.

## Sources

- [arXiv Query: search_query=cat:cs.RO&id_list=&start=0&max_results=30](https://arxiv.org/abs/2611.04477v1)

---
Canonical: https://techandbusiness.org/newswire/1O2i6_e6VkPQEgtI_gG5Od
Published: 2026-11-04T05:06:33.720Z
Story chronology: 2026-11-03T08:09:15.000Z
Retrieved: 2026-11-04T08:27:00.107Z
Publisher: Tech & Business (techandbusiness.org)