AgiBot GO-2 (Genie Operator-2)
No open weights, API or pricing found (GO-1 was open, non-commercial). Core work accepted to CVPR 2026 and ACL 2026 per AgiBot. Trained on 'tens of thousands of hours' of interaction data.
- Input
- image, text
- Output
- action
- License
- proprietary
How to call it
| Provider | Model id | Endpoint / URL | Docs |
|---|---|---|---|
| AgiBot robots / Genie Studio (via AgiBot sales) | — | www.agibot.com/article/231/detail/56.html | — |
Notable capabilities (3)
- Action chain-of-thought: Reasons in action space: generates a macro-plan of high-level action intents, then executes step by step, with teacher forcing so execution adheres to the reasoning. source
- Asynchronous dual-system: Low-frequency semantic planner ('commander') plus high-frequency action follower ('executor') in one architecture. source
- Benchmark results: LIBERO 98.5% average (ranked 1st), LIBERO-Plus 86.6% zero-shot, VLABench 47.4, 82.9% real-world success from simulation-only training (company-reported). source
Timeline entry
- AgiBot releases GO-2 embodied foundation model with action chain-of-thought ★★★
Shanghai's AgiBot released Genie Operator-2 (GO-2) on 2026-04-09, a VLA that plans in action space (action chain-of-thought) with an asynchronous slow-planner/fast-executor design; it reports 98.5% on LIBERO and 82.9% real-world success from simulation-only training.