Update README.md

README.md

@@ -1,3 +1,35 @@
----
-license: apache-2.0
----
+---
+license: mit
+language:
+- en
+pipeline_tag: image-text-to-text
+tags:
+- multimodal
+- gui-agent
+- reinforcement-learning
+---
+
+# Compress to Focus: Efficient Coordinate Compression for Policy Optimization in Multi-Turn GUI Agents
+
+Yurun Song*, Jiong Yin*, Rongjunchen Zhang, Ian Harris
+
+📖[Paper](https://arxiv.org/abs/2601.xxxxx) | 💻[Code](https://github.com/HiThink-Research/CCPO) | 🤗[Model-3b-3ao](https://huggingface.co/HiThink-Research/CCPO-3B-3AO-AITW) | 🤗Model-7b-3ao
+
+**CCPO** is a state-of-the-art multimodal GUI agent framework that couples visual compression with policy optimization. It introduces **Coordinate-Aware Spatial Compression (CASC)**, which aggregates coordinates from multiple rollouts to capture target-relevant regions and progressively narrow historical attention around key visual areas. We further design a **Distance-Based Advantage** that provides fine-grained learning signals based on distance rather than binary correctness. Extensive experiments demonstrate that CCPO achieves SOTA performance across four benchmarks with up to 55% token compression and 3.8x training speedup.
+
+## � Quick Start
+
+Please refer to our [GitHub Repository](https://github.com/HiThink-Research/CCPO) for the full agent pipeline including the **CASC** coordinate compression mechanism, as well as the training and evaluation scripts.
+
+## citation
+
+If you find this model useful, please cite our paper:
+
+```bibtex
+@inproceedings{song2026ccpo,
+  title={Compress to Focus: Efficient Coordinate Compression for Policy Optimization in Multi-Turn GUI Agents},
+  author={Yurun Song, Jiong Yin, Rongjunchen Zhang and Ian Harris},
+  booktitle={xxx},
+  year={2026}
+}
+```