Add missing metadata: library_name, license, and pipeline_tag

This PR adds the missing `library_name`, `license`, and `pipeline_tag` metadata to the model card. The model utilizes the Transformers library, is licensed under Apache 2.0, and performs text generation, which is reflected in the updated metadata. This improves the model card's completeness and discoverability on the Hugging Face Hub.

README.md

@@ -1,6 +1,9 @@
 ---
-{}
+license: apache-2.0
+library_name: transformers
+pipeline_tag: text-generation
 ---
+
 <h1 align="center">
 <em>AReaL</em>: Ant Reasoning Reinforcement Learning for LLMs
 </h1>
@@ -37,7 +40,7 @@ In our AReaL-boba² (A-ReaL-double-boba) release, we highlight the top 3 most im
 
 + Experimental support for **multi-turn** agentic RL training. Check our [complete example](https://inclusionai.github.io/AReaL/customization/agent.html).
 
-For the complete system design and more training details, please check [our v0.3 blog](/blog/AReaL_v0_3.md) and our [research paper](about:blank) for a more comprehensive presentation of our system design.
+For the complete system design and more training details, please check [our v0.3 blog](/blog/AReaL_v0_3.md) and our [research paper](https://arxiv.org/pdf/2505.24298).
 
 ### Overview of Asynchronous RL Training
 
@@ -100,8 +103,6 @@ AReaL-boba² allows you to independently customize the [dataset](https://inclusi
 
 In particular, we show a simple example to develop a multi-turn math agent for RL training. Please see the learning curve below and reference the [step-by-step guide](https://inclusionai.github.io/AReaL/customization/agent.html) if you want to implement your own agentic RL project.
 
-**Multi-turn Agent Learning Curve**
-
 ## Getting Started
 
 ### Quick Start
@@ -214,4 +215,4 @@ We also appreciate all the pioneering works from the community, particularly the
       primaryClass={cs.LG},
       url={https://arxiv.org/abs/2505.24298}, 
 }
-```
+```