Add pipeline tag and sample usage

README.md

@@ -2,14 +2,17 @@
 base_model:
 - Qwen/Qwen3.5-4B
 license: mit
+pipeline_tag: text-generation
+library_name: transformers
 ---
 
 # Sequential-Scaled-Solver-Qwen3.5-4B
 
-[🌐 Project Page](https://recursivemas.github.io) | [💻 Code](https://github.com/RecursiveMAS/RecursiveMAS) | [📄 Paper](https://arxiv.org/abs/2604.25917)
+[🌐 Project Page](https://recursivemas.github.io) | [💻 Code](https://github.com/RecursiveMAS/RecursiveMAS) | [📄 Paper](https://huggingface.co/papers/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 Sequential-Scaled setting, the Solver Agent is responsible for producing the final response based on the planning and critique information refined through RecursiveLink modules.
+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 **Sequential-Scaled** setting, the **Solver Agent** is responsible for producing the final response based on the planning and critique information refined through RecursiveLink modules.
 
 ## Model Details
 
@@ -20,8 +23,27 @@ RecursiveMAS treats a multi-agent system as a unified recursive computation, whe
 | Agent Role | Solver Agent |
 | 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).
+⚠️ **Note:** This checkpoint is a **role-specific agent** in [**RecursiveMAS**](https://huggingface.co/papers/2604.25917), rather than a standalone model intended for plain-text generation.
+
+## Usage
+
+To use this model within the RecursiveMAS framework, you can load the system using the provided system loader from the [official repository](https://github.com/RecursiveMAS/RecursiveMAS):
+
+```python
+from system_loader import load_mas_system
+
+# Load the full multi-agent system for the Sequential-Scaled style
+mas = load_mas_system(
+    style="sequential_scaled",
+    device="cuda",
+    trust_remote_code=True,
+)
+
+# Access the individual agent models
+planner = mas.agents["planner"].model
+critic = mas.agents["critic"].model
+solver = mas.agents["solver"].model
+```
 
 ## Model Collections for RecursiveMAS