Add pipeline tag and sample usage

This PR improves the model card by:
- Adding the `text-generation` pipeline tag to the YAML metadata for better discoverability.
- Adding a "Usage" section with a Python code snippet from the GitHub repository to demonstrate how to load the multi-agent system.
- Maintaining clear links to the paper, project page, and code.

README.md

@@ -2,6 +2,7 @@
 base_model:
 - Qwen/Qwen3.5-4B
 license: mit
+pipeline_tag: text-generation
 ---
 
 # Distillation-Learner-Qwen3.5-4B
@@ -21,7 +22,23 @@ RecursiveMAS treats a multi-agent system as a unified recursive computation, whe
 | Base Model | Qwen3.5-4B |
 
 ⚠️ **Note:** This checkpoint is a **role-specific agent** in [**RecursiveMAS**](https://arxiv.org/abs/2604.25917), rather than a standalone model intended for plain-text generation.  
-For detailed usage instructions, please refer to our [GitHub repository](https://github.com/RecursiveMAS/RecursiveMAS).
+
+## Usage
+
+For detailed environment setup and full training/inference instructions, please refer to the [GitHub repository](https://github.com/RecursiveMAS/RecursiveMAS). You can load the multi-agent system containing this agent using the following snippet:
+
+```python
+from system_loader import load_mas_system
+
+mas = load_mas_system(
+    style="distillation",
+    device="cuda",
+    trust_remote_code=True,
+)
+
+expert = mas.agents["expert"].model
+learner = mas.agents["learner"].model
+```
 
 ## Model Collections for RecursiveMAS
 
@@ -50,3 +67,4 @@ For detailed usage instructions, please refer to our [GitHub repository](https:/
       primaryClass={cs.AI},
       url={https://arxiv.org/abs/2604.25917}, 
 }
+```