Update README.md

README.md

@@ -18,8 +18,8 @@ A²FM achieves **state-of-the-art performance** on major reasoning and agentic b
 
 Notably, its adaptive execution achieves a **cost of pass of only \$0.00487 per correct answer**, cutting cost by **45.2% vs. reasoning** and **33.5% vs. agentic**, delivering substantially higher cost efficiency while maintaining comparable accuracy.
 
-📄 [**Paper (arXiv:2510.12838)**](https://arxiv.org/abs/2510.12838)  
-💻 [**GitHub (coming soon)**](https://github.com/OPPO-PersonalAI/Adaptive_Agent_Foundation_Models)
+📄 [**Paper**](https://arxiv.org/abs/2510.12838)  
+💻 [**GitHub**](https://github.com/OPPO-PersonalAI/Adaptive_Agent_Foundation_Models)
 
 ---