AgiBot GO-1 (Genie Operator-1)
Paper arXiv 2503.06669 (2025-03-09); announced ~2025-03-10 (day not re-verified). Weights on HF from Sept 2025, non-commercial license. Successor: agibot-go-2 (Apr 2026).
- Input
- image, text
- Output
- action
- License
- cc-by-nc-sa-4.0
- Verified
- 2026-09-29
How to call it
| Provider | Model id | Endpoint / URL | Docs |
|---|---|---|---|
| Hugging Face | agibot-world/GO-1 | huggingface.co/agibot-world/GO-1 | — |
| Hugging Face (lighter variant) | agibot-world/GO-1-Air | huggingface.co/agibot-world/GO-1-Air | — |
| GitHub | — | github.com/OpenDriveLab/Agibot-World | — |
Notable capabilities (1)
- Latent-action VLA trained on AgiBot World: 3B model on an InternVL2.5-2B backbone using latent action representations, pretrained on AgiBot World (1M+ trajectories, 217 tasks, 5 deployment scenarios); ~30% average gain over policies trained on Open X-Embodiment, 60%+ success on complex tasks, +32% vs RDT. source