diff --git a/README.md b/README.md
index cb6e887..c7d07c3 100644
--- a/README.md
+++ b/README.md
@@ -119,6 +119,8 @@ In the `owl/.env_example` file, you will find all the necessary API keys along w
 1. *Copy and Rename*: Duplicate the `.env_example` file and rename the copy to `.env`.
 2. *Fill in Your Keys*: Open the `.env` file and insert your API keys in the corresponding fields. 
 
+> **Note**: For optimal performance, we strongly recommend using OpenAI models. Our experiments show that other models may result in significantly lower performance on complex tasks and benchmarks.
+
 # 🚀 Quick Start
    
 Run the following minimal example:
diff --git a/owl/run.py b/owl/run.py
index 530e728..4b87651 100644
--- a/owl/run.py
+++ b/owl/run.py
@@ -33,14 +33,20 @@ def construct_society(question: str) -> OwlRolePlaying:
         model_config_dict=ChatGPTConfig(temperature=0, top_p=1).as_dict(), # [Optional] the config for model
     )
 
-    tools_list = [*WebToolkit(web_agent_model=assistant_model, planning_agent_model=assistant_model).get_tools(),
-    *DocumentProcessingToolkit().get_tools(),
-    *VideoAnalysisToolkit().get_tools(), # This requires OpenAI and Qwen Key
-    *CodeExecutionToolkit().get_tools(),
-    *ImageAnalysisToolkit(model=assistant_model).get_tools(),
-    *AudioAnalysisToolkit().get_tools(), # This requires OpenAI Key
-    *SearchToolkit(model=assistant_model).get_tools(),
-    *ExcelToolkit().get_tools()]
+    tools_list = [
+        *WebToolkit(
+            headless=False, 
+            web_agent_model=assistant_model, 
+            planning_agent_model=assistant_model
+        ).get_tools(),
+        *DocumentProcessingToolkit().get_tools(),
+        *VideoAnalysisToolkit().get_tools(),  # This requires OpenAI and Qwen Key
+        *CodeExecutionToolkit().get_tools(),
+        *ImageAnalysisToolkit(model=assistant_model).get_tools(),
+        *AudioAnalysisToolkit().get_tools(),  # This requires OpenAI Key
+        *SearchToolkit(model=assistant_model).get_tools(),
+        *ExcelToolkit().get_tools()
+    ]
 
     user_role_name = 'user'
     user_agent_kwargs = dict(model=user_model)
diff --git a/owl/run_gaia_roleplaying.py b/owl/run_gaia_roleplaying.py
index ac62839..4c6bb90 100644
--- a/owl/run_gaia_roleplaying.py
+++ b/owl/run_gaia_roleplaying.py
@@ -36,14 +36,20 @@ def main():
         model_config_dict=ChatGPTConfig(temperature=0, top_p=1).as_dict(), # [Optional] the config for model
     )
 
-    tools_list = [*WebToolkit(web_agent_model=assistant_model, planning_agent_model=assistant_model).get_tools(),
-    *DocumentProcessingToolkit().get_tools(),
-    *VideoAnalysisToolkit().get_tools(), # This requires OpenAI and Qwen Key
-    *CodeExecutionToolkit().get_tools(),
-    *ImageAnalysisToolkit(model=assistant_model).get_tools(),
-    *AudioAnalysisToolkit().get_tools(), # This requires OpenAI Key
-    *SearchToolkit(model=assistant_model).get_tools(),
-    *ExcelToolkit().get_tools()]
+    tools_list = [
+        *WebToolkit(
+            headless=False, 
+            web_agent_model=assistant_model, 
+            planning_agent_model=assistant_model
+        ).get_tools(),
+        *DocumentProcessingToolkit().get_tools(),
+        *VideoAnalysisToolkit().get_tools(),  # This requires OpenAI and Qwen Key
+        *CodeExecutionToolkit().get_tools(),
+        *ImageAnalysisToolkit(model=assistant_model).get_tools(),
+        *AudioAnalysisToolkit().get_tools(),  # This requires OpenAI Key
+        *SearchToolkit(model=assistant_model).get_tools(),
+        *ExcelToolkit().get_tools()
+    ]
 
     user_role_name = 'user'
     user_agent_kwargs = dict(model=user_model)
@@ -77,4 +83,3 @@ def main():
 
 if __name__ == "__main__":
     main()
-