Add custom banner, upgrade conclusion style

README.md

@@ -11,12 +11,9 @@ language:
 ---
 
 <p align="center">
-  <img src="benchmark_results.png" width="80%" alt="ComtradeBench Benchmark Results"/>
+  <img src="banner.png" width="100%" alt="ComtradeBench — An OpenEnv Benchmark for Reliable LLM Tool-Use"/>
 </p>
 
-<h1 align="center">ComtradeBench</h1>
-<h3 align="center">An OpenEnv Benchmark for Reliable LLM Tool-Use</h3>
-
 <p align="center">
   <a href="https://github.com/yonghongzhang-io/comtrade-openenv">
     <img src="https://img.shields.io/badge/GitHub-Repository-181717?logo=github" alt="GitHub"/>
@@ -239,7 +236,15 @@ All benchmark data is generated procedurally from a seeded PRNG — no external
 
 ## Conclusion
 
-> **Can an agent still finish the job when the API fights back?**
+<div align="center">
+<br>
+
+| |
+|:---:|
+| **Can an agent still finish the job when the API fights back?** |
+
+<br>
+</div>
 
 That question matters far beyond trade data. It applies to any agent expected to operate against real interfaces with pagination, retries, noisy outputs, and resource limits.