Add pipeline tag, library name, and sample usage

This PR improves the model card by adding the following:
- `pipeline_tag: text-generation`: Ensures the model is correctly categorized on the Hugging Face Hub.
- `library_name: transformers`: Based on the configuration files, this model is compatible with the `transformers` library.
- **Sample Usage**: A code snippet from the official GitHub repository has been added to demonstrate how to load this agent within the RecursiveMAS framework.

README.md

@@ -2,7 +2,10 @@
 base_model:
 - Qwen/Qwen3-1.7B
 license: mit
+library_name: transformers
+pipeline_tag: text-generation
 ---
+
 # Sequential-Light-Planner-Qwen3-1.7B
 
 [🌐 Project Page](https://recursivemas.github.io) | [💻 Code](https://github.com/RecursiveMAS/RecursiveMAS) | [📄 Paper](https://arxiv.org/abs/2604.25917)
@@ -23,6 +26,23 @@ RecursiveMAS treats a multi-agent system as a unified recursive computation, whe
 ⚠️ 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
+
+This model is intended to be used as part of the RecursiveMAS pipeline. Below is an example of how to load the system using the provided codebase:
+
+```python
+from system_loader import load_mas_system
+
+mas = load_mas_system(
+    style="sequential_light",
+    device="cuda",
+    trust_remote_code=True,
+)
+
+planner = mas.agents["planner"].model
+critic = mas.agents["critic"].model
+solver = mas.agents["solver"].model
+```
 
 ## Model Collections for RecursiveMAS
 
@@ -53,5 +73,4 @@ For detailed usage instructions, please refer to our [GitHub repository](https:/
       primaryClass={cs.AI},
       url={https://arxiv.org/abs/2604.25917}, 
 }
-```
-
+```