Add model card metadata and description

README.md

@@ -1,6 +1,36 @@
 ---
 license: apache-2.0
+pipeline_tag: text-generation
 ---
-The planner model to select perspectives. Should be combined with BGE-M3 encoder.
 
-Refer to https://github.com/ulab-uiuc/DRPG-RebuttalAgent for usage.
+# DRPG Planner
+
+The planner model used to select perspectives within the **DRPG** (Decompose, Retrieve, Plan, Generate) framework. It is designed to be used in conjunction with a BGE-M3 encoder to identify the most feasible rebuttal directions.
+
+- **Paper:** [DRPG (Decompose, Retrieve, Plan, Generate): An Agentic Framework for Academic Rebuttal](https://huggingface.co/papers/2601.18081)
+- **Repository:** [ulab-uiuc/DRPG-RebuttalAgent](https://github.com/ulab-uiuc/DRPG-RebuttalAgent)
+
+## About DRPG
+DRPG is an agentic framework for automatic academic rebuttal generation. It addresses the challenges of long-context understanding and persuasive response generation in peer review through a four-step process:
+1. **Decompose**: Breaking reviews into atomic concerns.
+2. **Retrieve**: Extracting relevant evidence from the paper.
+3. **Plan**: Using this **Planner** model to identify the most feasible rebuttal strategies (achieving over 98% accuracy in perspective selection).
+4. **Generate**: Creating the final response based on the plan and evidence.
+
+Experiments on data from top-tier conferences demonstrate that DRPG significantly outperforms existing rebuttal pipelines and achieves performance beyond the average human level using only an 8B model.
+
+## Usage
+
+Refer to the official [GitHub repository](https://github.com/ulab-uiuc/DRPG-RebuttalAgent) for complete usage instructions and implementation details.
+
+## Citation
+
+```bibtex
+@article{han2025drpg,
+  title={DRPG (Decompose, Retrieve, Plan, Generate): An Agentic Framework for Academic Rebuttal},
+  author={Han, Peixuan and Yu, Yingjie and Xu, Jingjun and You, Jiaxuan},
+  journal={arXiv preprint arXiv:2601.18081},
+  url={https://arxiv.org/pdf/2601.18081},
+  year={2026}
+}
+```