feat: add benchmarking GIF to README and Swarm Intro documentation for improved visualization

Author: binary-husky

README.md

@@ -89,6 +89,11 @@ Explore our rich library of examples to kickstart your journey:
 - 🎴 [**Writing a countdown game using AgentScope and solving it**](https://modelscope.github.io/AgentJet/en/example_countdown).
 - 🚶 [**Solving a frozen lake walking puzzle using AgentJet**](https://modelscope.github.io/AgentJet/en/example_frozenlake).
 
+Explore our automated benchmarking system [https://benchmark.agentjet.top/](https://benchmark.agentjet.top/):
+<div align="center">
+<img width="600" alt="image" src="https://serve.gptacademic.cn/publish/shared/Image/benchmark.gif"/>
+</div>
+
 
 ---
 

docs/en/swarm_intro.md

@@ -182,7 +182,9 @@ AgentJet 在工程质量上投入了大量精力，确保每一次训练结果
 - **Token一致性自动告警&修复**：AgentJet默认情况下会自动根据 vLLM 引擎返回的 Token ID 进行 Re-tokenization 漂移修复。
 - **多训练后端支持**：支持包括 VERL 在内的多个训练后端，正着手支持 TRL 等其他训练后端。
 
-
+<div align="center">
+<img width="600" alt="image" src="https://serve.gptacademic.cn/publish/shared/Image/benchmark.gif"/>
+</div>
 
 
 ## 总结与展望