Update README.md

README.md

@@ -18,33 +18,62 @@ base_model: Qwen/Qwen3-1.7B
 ---
 # AutoGEO_mini_Qwen1.7B_GEOBench
 
-A lightweight **web-document rewriting** model fine-tuned with **GRPO** (reinforcement learning) from **Qwen3-1.7B**, developed as part of the AutoGEO framework introduced in:
+# AutoGEO<sub>Mini</sub> (Qwen1.7B, GEOBench)
 
-**WHAT GENERATIVE SEARCH ENGINES LIKE AND HOW TO OPTIMIZE WEB CONTENT COOPERATIVELY**  
-Paper (arXiv): https://arxiv.org/abs/2510.11438
+AutoGEO<sub>Mini</sub> (Qwen1.7B, GEOBench) is a GEO model designed to improve how web document is incorporated into answers generated by **LLM-based search engines**.
 
----
+The model rewrites a given document to better match the preferences of generative engines (e.g., GPT, Gemini, Claude), with the goal of increasing the document’s **visibility and coverage** in generated responses, while **preserving the original meaning and factual content**.
 
-## What this model does
+This model is part of the **AutoGEO** framework proposed in the paper
 
-**AutoGEO_mini_Qwen1.7B_GEOBench** rewrites raw web documents into improved versions that are better aligned with generative search engines’ preferences for **GEO-Bench dataset**.
+📄 **Paper:** ["What Generative Search Engines Like and How to Optimize Web Content Cooperatively"](https://arxiv.org/abs/2510.11438)  
+👥 **Authors:** Yujiang Wu*, Shanshan Zhong*, Yubin Kim, Chenyan Xiong (*Equal contribution)  
+🚀 **Code:** [AutoGEO on GitHub](https://github.com/cxcscmu/AutoGEO)  
 
-In our experiments/usage:
-- The total cost is about **0.0071×** the cost of **gemini-2.5-pro** for comparable rewriting workloads.
-- Rewritten documents achieve **significant improvements in GEO metrics**.
+## Usage
 
----
+This model is designed to be used through the [**AutoGEO framework**](https://github.com/cxcscmu/AutoGEO). Try it out in [huggingface Space](https://huggingface.co/spaces/cx-cmu/AutoGEO_Mini) or
 
-## Training summary
+Quick starts:
 
-- **Base model:** Qwen3-1.7B
-- **Method:** GRPO-based reinforcement learning fine-tuning
-- **Task:** Rewrite original web documents to improve GEO metrics (per the AutoGEO framework in the paper above)
+```python
+from autogeo.rewriters import rewrite_document
 
----
+rewritten_text = rewrite_document(
+    document="Input text.",
+    dataset="GEOBench",
+    engine_llm="gemini",
+    model_path="cx-cmu/AutoGEO_mini_Qwen1.7B_ResearchyGEO",
+)
+```
+
+Evaluation:
+
+```bash
+python -m autogeo.evaluate \
+  --model autogeo_mini \
+  --model_path cx-cmu/AutoGEO_mini_Qwen1.7B_ResearchyGEO \
+  --dataset GEOBench
+```
+
+
+
+## Related Resources
+
+* **Paper:** [https://arxiv.org/abs/2510.11438](https://arxiv.org/abs/2510.11438)
+* **Code:** [https://github.com/cxcscmu/AutoGEO](https://github.com/cxcscmu/AutoGEO)
+* **Demo:** [https://huggingface.co/spaces/cx-cmu/AutoGEO_Mini](https://huggingface.co/spaces/cx-cmu/AutoGEO_Mini)
+* **Dataset:** [https://huggingface.co/datasets/cx-cmu/GEOBench](https://huggingface.co/datasets/cx-cmu/GEOBench)
 
-## Repository contents
+## Citation
 
-This repository includes the standard inference artifacts (e.g., `model.safetensors`, `config.json`, `tokenizer.json`, `chat_template.jinja`, etc.) required to load and run the model with `transformers`.
+If you use this model, please cite:
 
----
+```bibtex
+@article{wu2025generative,
+  title={What Generative Search Engines Like and How to Optimize Web Content Cooperatively},
+  author={Wu, Yujiang and Zhong, Shanshan and Kim, Yubin and Xiong, Chenyan},
+  journal={arXiv preprint arXiv:2510.11438},
+  year={2025}
+}
+```