diff --git a/en/config/agent-runners/astrbot-agent-runner.md b/en/config/agent-runners/astrbot-agent-runner.md
index 74873d7..17e5e22 100644
--- a/en/config/agent-runners/astrbot-agent-runner.md
+++ b/en/config/agent-runners/astrbot-agent-runner.md
@@ -6,3 +6,14 @@ By default, AstrBot uses the built-in Agent Runner as the default executor. You
 
 With the built-in Agent Runner, you can use AstrBot's [MCP Server](/use/mcp), [Knowledge Base](/use/knowledge-base), [Web Search](/use/websearch), and persona features.
 
+## Follow-up Message Handling
+
+When the Agent is executing tool calls (such as web search, code execution, etc.), new messages sent by the user are automatically captured and queued. These follow-up messages are injected into the context when the next tool result is returned, allowing the LLM to prioritize them.
+
+This feature allows users to continue the conversation while the Agent is performing long-running tasks, without waiting for the current task to complete. The Agent will respond to your follow-up messages immediately after processing the current tool call.
+
+**Example Use Cases:**
+
+- While the Agent is performing a web search, you can send "also search for XXX"
+- While the Agent is calling the code executor, you can add new instructions or modify requirements
+- Multiple follow-up messages are processed in the order they were sent
\ No newline at end of file
diff --git a/en/use/function-calling.md b/en/use/function-calling.md
index e3df83d..cad0c9f 100644
--- a/en/use/function-calling.md
+++ b/en/use/function-calling.md
@@ -46,6 +46,16 @@ Below are some common tool calling demos:
 ![image](https://files.astrbot.app/docs/source/images/function-calling/image-1.png)
 
 
+## Follow-up Messages During Tool Execution
+
+When the Agent is executing tool calls, new messages you send are automatically captured and queued. These follow-up messages are injected into the context when the next tool result is returned, allowing the LLM to prioritize them.
+
+For example, while the Agent is performing a web search, you can continue to send "also search for XXX", and the Agent will respond to your follow-up request immediately after processing the current search.
+
+:::tip
+This feature is only available when using the AstrBot built-in Agent Runner.
+:::
+
 ## MCP
 
-Please refer to this documentation: [AstrBot - MCP](/use/mcp).
+Please refer to this documentation: [AstrBot - MCP](/use/mcp).
\ No newline at end of file
diff --git a/zh/config/agent-runners/astrbot-agent-runner.md b/zh/config/agent-runners/astrbot-agent-runner.md
index 89f8fa8..b697cf8 100644
--- a/zh/config/agent-runners/astrbot-agent-runner.md
+++ b/zh/config/agent-runners/astrbot-agent-runner.md
@@ -6,3 +6,14 @@
 
 在内置 Agent 执行器下，您可以使用 AstrBot 的 [MCP 服务器](/use/mcp)、[知识库](/use/knowledge-base)、[网页搜索](/use/websearch)、人格功能。
 
+## 后续消息处理
+
+当 Agent 正在执行工具调用（如网页搜索、代码执行等）时，用户发送的新消息会被自动捕获并排队。这些后续消息会在下一次工具结果返回时被注入到上下文中，让 LLM 能够优先处理这些消息。
+
+这一特性使得用户可以在 Agent 执行长时间任务时继续对话，而无需等待当前任务完成。Agent 会在处理完当前工具调用后，立即响应您的后续消息。
+
+**使用场景示例：**
+
+- Agent 正在执行网页搜索时，您可以发送"顺便也搜索一下 XXX"
+- Agent 正在调用代码执行器时，您可以补充新的指令或修改需求
+- 多条后续消息会按发送顺序依次处理
\ No newline at end of file
diff --git a/zh/use/function-calling.md b/zh/use/function-calling.md
index aa1cb15..945ad72 100644
--- a/zh/use/function-calling.md
+++ b/zh/use/function-calling.md
@@ -8,7 +8,7 @@ outline: deep
 
 函数调用旨在提供大模型**调用外部工具的能力**，以此实现 Agentic 的一些功能。
 
-比如，问大模型：帮我搜索一下关于“猫”的信息，大模型会调用用于搜索的外部工具，比如搜索引擎，然后返回搜索结果。
+比如，问大模型：帮我搜索一下关于"猫"的信息，大模型会调用用于搜索的外部工具，比如搜索引擎，然后返回搜索结果。
 
 目前，支持的模型包括但不限于
 
@@ -46,6 +46,16 @@ outline: deep
 ![image](https://files.astrbot.app/docs/source/images/function-calling/image-1.png)
 
 
+## 工具执行期间的后续消息
+
+当 Agent 正在执行工具调用时，您发送的新消息会被自动捕获并排队。这些后续消息会在下一次工具结果返回时被注入到上下文中，让 LLM 能够优先处理。
+
+例如，当 Agent 正在执行网页搜索时，您可以继续发送"顺便也搜索一下 XXX"，Agent 会在处理完当前搜索后立即响应您的后续请求。
+
+:::tip
+此功能仅在使用 AstrBot 内置 Agent 执行器时可用。
+:::
+
 ## MCP
 
 请前往此文档 [AstrBot - MCP](/use/mcp) 查看。
\ No newline at end of file