Improve model card: add pipeline tag, library name, and links
#1
by nielsr HF Staff - opened
README.md
CHANGED
|
@@ -1,11 +1,30 @@
|
|
| 1 |
---
|
| 2 |
-
license: mit
|
| 3 |
language:
|
| 4 |
- en
|
| 5 |
-
|
| 6 |
-
|
|
|
|
| 7 |
---
|
| 8 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
|
| 10 |
## Citation
|
| 11 |
|
|
@@ -18,3 +37,4 @@ If you find this model useful, please cite our paper:
|
|
| 18 |
journal={arXiv preprint arXiv:2602.16855},
|
| 19 |
year={2026}
|
| 20 |
}
|
|
|
|
|
|
| 1 |
---
|
|
|
|
| 2 |
language:
|
| 3 |
- en
|
| 4 |
+
license: mit
|
| 5 |
+
pipeline_tag: image-text-to-text
|
| 6 |
+
library_name: transformers
|
| 7 |
---
|
| 8 |
|
| 9 |
+
# Mobile-Agent-v3.5 (GUI-Owl-1.5)
|
| 10 |
+
|
| 11 |
+
[Mobile-Agent-v3.5](https://huggingface.co/papers/2602.16855), also referred to as **GUI-Owl-1.5**, is a family of native multi-platform GUI agent foundation models. It is designed to enable cloud-edge collaboration and real-time interaction across a range of platforms, including desktop (Windows, Linux, MacOS), mobile (Android), and browsers.
|
| 12 |
+
|
| 13 |
+
## Model Description
|
| 14 |
+
|
| 15 |
+
GUI-Owl-1.5 is a native end-to-end multimodal agent that unifies perception, grounding, reasoning, planning, and action execution within a single policy network. It achieves state-of-the-art results on more than 20 GUI benchmarks, including OSWorld, AndroidWorld, and WebArena.
|
| 16 |
+
|
| 17 |
+
Key features include:
|
| 18 |
+
- **Multi-platform support**: Unified automation capabilities for mobile, desktop, and web environments.
|
| 19 |
+
- **Thinking & Instruct Variants**: Features models optimized for both direct instruction following and complex reasoning.
|
| 20 |
+
- **Unified Reasoning**: Uses a thought-synthesis pipeline to enhance decision-making and tool-calling (MCP) capabilities.
|
| 21 |
+
- **MRPO Algorithm**: A new environment RL algorithm designed to address multi-platform conflicts and improve training efficiency for long-horizon tasks.
|
| 22 |
+
|
| 23 |
+
## Resources
|
| 24 |
+
|
| 25 |
+
- **Paper:** [Mobile-Agent-v3.5: Multi-platform Fundamental GUI Agents](https://huggingface.co/papers/2602.16855)
|
| 26 |
+
- **Code:** [GitHub - X-PLUG/MobileAgent](https://github.com/X-PLUG/MobileAgent)
|
| 27 |
+
- **Model Collection:** [GUI-Owl-1.5 Collection](https://huggingface.co/collections/mPLUG/gui-owl-15)
|
| 28 |
|
| 29 |
## Citation
|
| 30 |
|
|
|
|
| 37 |
journal={arXiv preprint arXiv:2602.16855},
|
| 38 |
year={2026}
|
| 39 |
}
|
| 40 |
+
```
|