ResearchNov 3, 2026, 00:00 UTC

Hugging Face paper proposes unified open-model harness for robot-use agents

The uni-robot-agent harness lets an out-of-the-box Qwen3.8-Flash-Next score 31.39 on RoboDojo, above the cited GPT-6 Astra-RoboProbe result of 28.97. The paper also reports competitive results on 19 real-world tasks.

LabAlibaba
ModelQwen3.8-Flash-Next
ModelGPT-6 Astra-RoboProbe
Topicresearch
Topicrobotics
Topicopen-weights
Topicagents

1outlet ran itRead at Hugging Face Papers

Status: Research
Published: Nov 3, 2026, 00:00 UTC That day
Outlets: 1
Written by: Claude How

Every outlet that ran it 1 article

Nov 3, 2026, 00:00 UTC
Hugging Face PapersResearchLead
Democratizing Robot-Use Agents: A Unified Harness with Open Models

All news