Add model metadata and update paper links

Hi! I'm Niels from the Hugging Face community science team. I'm opening this PR to improve the model card for AdaReasoner.

Specifically, I have:
- Added `pipeline_tag: image-text-to-text` to ensure the model is correctly categorized on the Hub.
- Added `library_name: transformers` as the model uses the Qwen2.5-VL architecture.
- Included the `license: apache-2.0` in the metadata.
- Updated the "Paper" badge and introductory text to link directly to the research paper on arXiv.
- Added descriptive tags like `tool-use` and `visual-reasoning`.

This metadata will help users discover and use your model more effectively. Let me know if you have any questions!

README.md

@@ -1,8 +1,20 @@
+---
+license: apache-2.0
+library_name: transformers
+pipeline_tag: image-text-to-text
+tags:
+- multimodal
+- visual-reasoning
+- tool-use
+- reasoning
+base_model: Qwen/Qwen2.5-VL-7B-Instruct
+---
+
 <div align="center">
   <img src="docs/logo.png" alt="Logo" width="300">
   <h1 align="center">Dynamic Tool Orchestration for Iterative Visual Reasoning</h1>
 
-  <a href="#">
+  <a href="https://arxiv.org/abs/2601.18631">
     <img src="https://img.shields.io/badge/Paper-A42C25?style=for-the-badge&logo=arxiv&logoColor=white" alt="Paper">
   </a>
   <a href="https://github.com/ssmisya/AdaReasoner/tree/main/docs">
@@ -24,6 +36,7 @@
     
 </div>
 
+This repository contains the weights for **AdaReasoner-7B**, presented in [AdaReasoner: Dynamic Tool Orchestration for Iterative Visual Reasoning](https://arxiv.org/abs/2601.18631).
 
 ## 🔔 Important Note on Model Status
 
@@ -45,20 +58,14 @@ We provide three variants of AdaReasoner-7B, each optimized for different use ca
 | **AdaReasoner-TC-7B-Randomized** | Trained with the *adaptive learning* method, enabling strong generalization to **unseen tools and tasks**. Designed for open-ended and evolving tool environments where adaptability is required. | [🤗 Link](https://huggingface.co/AdaReasoner/AdaReasoner-TC-7B-Randomized) |
 | **AdaReasoner-TC-7B-Non-Randomized** | Trained **without adaptive learning**, providing **more stable and reliable performance on known tools and tasks**, but limited generalization to unseen tools or task settings. | [🤗 Link](https://huggingface.co/AdaReasoner/AdaReasoner-TC-7B-Non-Randomized) |
 
-
-
-
 **Key Differences:**
 - **Randomized**: Trained with adaptive learning method, enabling zero-shot generalization to novel tools and task configurations
 - **Non-Randomized**: Trained without adaptive learning, offering more predictable behavior on familiar tools but lacking generalization
 
-
-
 ## 📊 Performance
 
 Please refer to our paper for detailed benchmark results across multiple visual reasoning tasks.
 
-
 ## 📚 Citation
 
 If you use this model in your research, please cite:
@@ -82,4 +89,4 @@ This model is part of the AdaReasoner project. For more information, visit our [
 
 ## 📧 Contact
 
-For questions and feedback, please open an issue in our [GitHub repository](https://github.com/ssmisya/AdaReasoner).
+For questions and feedback, please open an issue in our [GitHub repository](https://github.com/ssmisya/AdaReasoner).