From 699ce7e97fe31be5dfe3445502cfda4e19b83534 Mon Sep 17 00:00:00 2001
From: NSigma <zhun.wang@berkeley.edu>
Date: Mon, 2 Jun 2025 22:36:49 -0700
Subject: [PATCH] Update README.md

---
 README.md | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/README.md b/README.md
index 75b356e..b7aebc9 100644
--- a/README.md
+++ b/README.md
@@ -5,6 +5,8 @@
 [![Hugging Face](https://img.shields.io/badge/HuggingFace-zzzz-orange?logo=huggingface&logoColor=white)](https://huggingface.co/zzzz)
 [![License](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](LICENSE)
 
+CyberGym is a large-scale, high-quality cybersecurity evaluation framework designed to rigorously assess the capabilities of AI agents on real-world vulnerability analysis tasks.
+
 ## Installation
 Require python and docker environment.
 
@@ -113,11 +115,11 @@ git submodule update --init --recursive examples/agents
 Then check the instructions in the folder: [Example Agents](examples/agents/README.md)
 
 
-# Citation
+## Citation
 If you use this project in your research, please cite:
 ```
 TODO
 ```
 
-# License
+## License
 This project is licensed under the [Apache License 2.0](LICENSE).