Update README.md

README.md

@@ -1,12 +1,31 @@
 ---
-title: Reasoning Earlystop
-emoji: 🏢
-colorFrom: pink
+title: Answer Convergence Early Stopping
+emoji: 🛑
+colorFrom: indigo
 colorTo: red
 sdk: gradio
-sdk_version: 6.2.0
+sdk_version: 5.0.0
 app_file: app.py
 pinned: false
+license: mit
+short_description: Demo for EMNLP Paper "Answer Convergence as a Signal..."
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# 🛑 Answer Convergence as a Signal for Early Stopping in Reasoning
+
+### [EMNLP Accepted] | [Paper (arXiv)](https://arxiv.org/abs/2506.02536) | [GitHub Code](https://github.com/launchnlp/reasoning_earlystop)
+
+**Authors:** Xin Liu, Lu Wang (University of Michigan)
+
+---
+
+## 💡 What is this?
+This Space demonstrates the core concept of our paper: **Large Language Models often internally converge on an answer long before they finish generating the full reasoning chain.**
+
+By detecting this **Answer Convergence**, we can stop the generation early, saving **40%+** of inference costs without sacrificing accuracy.
+
+## 🚀 Key Methods
+We propose three strategies to detect this signal:
+1.  **Answer Consistency:** Unsupervised method checking if the answer stabilizes across reasoning chunks.
+2.  **Think Token Adjustment:** Encouraging the model to output the stop signal earlier.
+3.  **Learn-to-Stop:** A lightweight supervised module trained on internal activations.