diff --git a/README.md b/README.md
index ae71da9..48ed53a 100644
--- a/README.md
+++ b/README.md
@@ -86,6 +86,7 @@ We do not test or recommend using `gpt-3.5-turbo` to run XAgent due to very limi
 ```bash
 python run.py --task "put your task here" --model "gpt-4"
 ```
+You can use argument `--upload_files` to select files you want to submit to XAgent.
 The local workspace for your XAgent is in `local_workspace`, where you can find all the files generated by XAgent throughout the running process. Besides, in `running_records` you can find all the intermediate steps information, e.g. task statuses, LLM's input-output pairs, used tools, etc.
 After execution, the full `workspace` in `ToolServerNode` will be copied to `running_records` for your convenience.
 
@@ -97,7 +98,7 @@ docker compose up
 
 cd ../XAgentWeb
 npm install
-npm run serve
+npm run dev
 ```
 Build the docker image for XAgent-Server and start the docker container.
 You will see the XAgent Server listening on port `8000`.
diff --git a/README_ZH.md b/README_ZH.md
index 2f1dce3..ad0b054 100644
--- a/README_ZH.md
+++ b/README_ZH.md
@@ -83,6 +83,7 @@ pip install -r requirements.txt
 ```bash
 python run.py --task "put your task here" --model "gpt-4"
 ```
+您可以使用参数`--upload_files`来指定提交给XAgent的文件。
 您的XAgent的本地工作空间在`local_workspace`中，您可以在运行过程中找到XAgent生成的所有文件。
 此外，在`running_records`中，您可以找到所有的中间步骤信息，例如任务状态、LLM的输入输出对、使用的工具等。
 在运行结束后，`ToolServerNode`中的完整`worksapce`也将被打包下载到其中。
@@ -95,7 +96,7 @@ docker compose up
 
 cd ../XAgentWeb
 npm install
-npm run serve
+npm run dev
 ```
 构建XAgent-Server的docker镜像并启动docker容器。
 您将看到XAgent Server在端口`8000`上监听。