Improve model card metadata and content

Hi! I'm Niels from the Hugging Face community team. I've updated your model card to improve its metadata and discoverability.

Summary of changes:
- Added `pipeline_tag: image-text-to-text` to the metadata.
- Linked the repository to the [Mobile-Agent-v3.5 paper](https://huggingface.co/papers/2602.16855) and its [official GitHub repository](https://github.com/X-PLUG/MobileAgent).
- Cleaned up the YAML metadata by moving the ArXiv reference to the markdown section.

This should make it easier for users to find your model and the associated research!

README.md

@@ -1,11 +1,19 @@
 ---
-license: mit
 language:
 - en
-tags:
-- arxiv:2602.16855
+license: mit
+pipeline_tag: image-text-to-text
 ---
 
+# Mobile-Agent-v3.5 (GUI-Owl-1.5)
+
+**Mobile-Agent-v3.5** introduces **GUI-Owl-1.5**, a family of native multi-platform GUI agent foundation models. Built on the Qwen3-VL architecture, GUI-Owl-1.5 supports automation across desktop, mobile, and browser platforms, achieving state-of-the-art results on more than 20 GUI benchmarks like OSWorld, AndroidWorld, and WebArena.
+
+It unifies perception, grounding, reasoning, planning, and action execution within a single policy network, supporting both "Instruct" and "Thinking" variants.
+
+- **Paper:** [Mobile-Agent-v3.5: Multi-platform Fundamental GUI Agents](https://huggingface.co/papers/2602.16855)
+- **Repository:** [https://github.com/X-PLUG/MobileAgent](https://github.com/X-PLUG/MobileAgent)
+- **Project Page:** [Mobile-Agent Family](https://github.com/X-PLUG/MobileAgent)
 
 ## Citation
 
@@ -18,3 +26,4 @@ If you find this model useful, please cite our paper:
   journal={arXiv preprint arXiv:2602.16855},
   year={2026}
 }
+```