Add pipeline tag and sample usage

This PR improves the model card by:
1. Adding the `text-generation` pipeline tag to the YAML metadata for better discoverability.
2. Including a **Sample Usage** section demonstrating how to load this specific agent within the RecursiveMAS framework, as documented in the official GitHub repository.
3. Ensuring consistent formatting for model details and links to the paper and code.

README.md

@@ -2,14 +2,15 @@
 base_model:
 - Qwen/Qwen3.5-4B
 license: mit
+pipeline_tag: text-generation
 ---
 
 # Deliberation-Reflector-Qwen3.5-4B
 
 [🌐 Project Page](https://recursivemas.github.io) | [💻 Code](https://github.com/RecursiveMAS/RecursiveMAS) | [📄 Paper](https://arxiv.org/abs/2604.25917)
 
-We introduce RecursiveMAS, a multi-agent framework that scales agent collaboration through latent-space recursion.
-RecursiveMAS treats a multi-agent system as a unified recursive computation, where heterogeneous agents iteratively exchange, refine, and evolve their latent states across recursion rounds. In the Deliberation-Style setting, the Reflector Agent reviews and refines the reasoning process, while collaborating with the Tool-Caller Agent through RecursiveLink modules for iterative improvement.
+We introduce **RecursiveMAS**, a multi-agent framework that scales agent collaboration through latent-space recursion. 
+RecursiveMAS treats a multi-agent system as a unified recursive computation, where heterogeneous agents iteratively exchange, refine, and evolve their latent states across recursion rounds. In the **Deliberation-Style** setting, the **Reflector Agent** reviews and refines the reasoning process, while collaborating with the Tool-Caller Agent through RecursiveLink modules for iterative improvement.
 
 ## Model Details
 
@@ -21,7 +22,24 @@ 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).
+
+## Sample Usage
+
+To use this model, you should load the entire multi-agent system using the official system loader as described in the [GitHub repository](https://github.com/RecursiveMAS/RecursiveMAS):
+
+```python
+from system_loader import load_mas_system
+
+# Load the full deliberation multi-agent system
+mas = load_mas_system(
+    style="deliberation",
+    device="cuda",
+    trust_remote_code=True,
+)
+
+# Access the individual reflector agent
+reflector = mas.agents["reflector"].model
+```
 
 ## Model Collections for RecursiveMAS