Democratizing Robot-Use Agents: A Unified Harness with Open Models
Overview
This paper introduces uni-robot-agent, an open-weight harness for robot-use agents that supports further training without relying on proprietary models. Using Qwen3.8-Flash-Next out-of-the-box, the system achieves a RoboDojo Score of 31.39, surpassing the published GPT-6 Astra-RoboProbe result of 28.97 and performing competitively on 19 real-world tasks. The authors analyze model generations, families, and sizes to link effective robot use to four general capabilities, suggesting future training should develop them jointly.
Generated from attributed reports · Updated 3 hours ago
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
Reported quantity · RoboDojo Score: 31.39 other · Basis not reported
“ash-Next achieves a RoboDojo Score of 31.39, surpassing the published GPT-6 Astra-RoboProbe result of 28.97 and many VLA/WAM baselines, and performs competitively on 19 real-world tasks. Our analysis across model generations, families, and sizes links effective robot use to four general capabilities, suggesting that future RUA training should develop them jointly.”
Exact source · revision 2Source owner not reported
Reported quantity · GPT-6 Astra-RoboProbe RoboDojo Score: 28.97 other · Basis not reported
“ash-Next achieves a RoboDojo Score of 31.39, surpassing the published GPT-6 Astra-RoboProbe result of 28.97 and many VLA/WAM baselines, and performs competitively on 19 real-world tasks. Our analysis across model generations, families, and sizes links effective robot use to four general capabilities, suggesting that future RUA training should develop them jointly.”
Exact source · revision 2Source owner not reported
Reported quantity · RoboDojo Score (GPT-6 Astra-RoboProbe): 28.97 other · Basis not reported
“ash-Next achieves a RoboDojo Score of 31.39, surpassing the published GPT-6 Astra-RoboProbe result of 28.97 and many VLA/WAM baselines, and performs competitively on 19 real-world tasks. Our analysis across model generations, families, and sizes links effective robot use to four general capabilities, suggesting that future RUA training should develop them jointly.”
Exact source · revision 2Source owner not reported
Reported quantity · RoboDojo Score (uni-robot-agent): 31.39 other · Basis not reported
“ash-Next achieves a RoboDojo Score of 31.39, surpassing the published GPT-6 Astra-RoboProbe result of 28.97 and many VLA/WAM baselines, and performs competitively on 19 real-world tasks. Our analysis across model generations, families, and sizes links effective robot use to four general capabilities, suggesting that future RUA training should develop them jointly.”
Exact source · revision 2Source owner not reported
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsSignalDemocratizing Robot-Use Agents: A Unified Harness with Open Models
This paper introduces uni-robot-agent, an open-weight harness for robot-use agents that supports further training without relying on proprietary models. Using Qwen3.8-Flash-Next out-of-the-box, the system achieves a RoboDojo Score of 31.39, surpassing the published GPT-6 Astra-RoboProbe result of 28.97 and performing competitively on 19 real-world tasks. The authors analyze model generations, families, and sizes to link effective robot use to four general capabilities, suggesting future training should develop them jointly.
Event coverage history
Current attention 4·Peak within the comparable range 5（2026-11-04 09:00 UTC）·Change within the comparable range over 24 hours –
The trend compares participants observed continuously; its scope may be narrower than current attention totals. Hover or click to explore hourly observations, or use the left and right arrow keys.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).