InfiX-ai
/

InfiGUI-R1-3B

@@ -56,47 +56,11 @@ new_height, new_width = smart_resize(height, width, max_pixels=MAX_IMAGE_PIXELS)
 # Prepare inputs
 instruction = "View detailed storage space usage"
-system_prompt = "You FIRST think about the reasoning process as an internal monologue and then provide the final answer.
-The reasoning process MUST BE enclosed within <think> </think> tags."
-tool_prompt = "
-# Tools
-You may call one or more functions to assist with the user query.
-You are provided with function signatures within <tools></tools> XML tags:
-<tools>
-{\"type\": \"function\", \"function\": {\"name\": \"mobile_use\", \"description\": \"Use a touchscreen to interact with a mobile device, and take screenshots.\
-* This is an interface to a mobile device with touchscreen. You can perform actions like clicking, typing, swiping, etc.\
-* Some applications may take time to start or process actions, so you may need to wait and take successive screenshots to see the results of your actions.\
-* The screen's resolution is " + str(new_width) + "x" + str(new_height) + ".\
-* Make sure to click any buttons, links, icons, etc with the cursor tip in the center of the element. Don't click boxes on their edges unless asked.\", \"parameters\": {\"properties\": {\"action\": {\"description\": \"The action to perform. The available actions are:\
-* `key`: Perform a key event on the mobile device.\
-    - This supports adb's `keyevent` syntax.\
-    - Examples: \\\"volume_up\\\", \\\"volume_down\\\", \\\"power\\\", \\\"camera\\\", \\\"clear\\\".\
-* `click`: Click the point on the screen with coordinate (x, y).\
-* `long_press`: Press the point on the screen with coordinate (x, y) for specified seconds.\
-* `swipe`: Swipe from the starting point with coordinate (x, y) to the end point with coordinates2 (x2, y2).\
-* `type`: Input the specified text into the activated input box.\
-* `system_button`: Press the system button.\
-* `open`: Open an app on the device.\
-* `wait`: Wait specified seconds for the change to happen.\
-* `terminate`: Terminate the current task and report its completion status.\", \"enum\": [\"key\", \"click\", \"long_press\", \"swipe\", \"type\", \"system_button\", \"open\", \"wait\", \"terminate\"], \"type\": \"string\"}, \"coordinate\": {\"description\": \"(x, y): The x (pixels from the left edge) and y (pixels from the top edge) coordinates to move the mouse to. Required only by `action=click`, `action=long_press`, and `action=swipe`.\", \"type\": \"array\"}, \"coordinate2\": {\"description\": \"(x, y): The x (pixels from the left edge) and y (pixels from the top edge) coordinates to move the mouse to. Required only by `action=swipe`.\", \"type\": \"array\"}, \"text\": {\"description\": \"Required only by `action=key`, `action=type`, and `action=open`.\", \"type\": \"string\"}, \"time\": {\"description\": \"The seconds to wait. Required only by `action=long_press` and `action=wait`.\", \"type\": \"number\"}, \"button\": {\"description\": \"Back means returning to the previous interface, Home means returning to the desktop, Menu means opening the application background menu, and Enter means pressing the enter. Required only by `action=system_button`\", \"enum\": [\"Back\", \"Home\", \"Menu\", \"Enter\"], \"type\": \"string\"}, \"status\": {\"description\": \"The status of the task. Required only by `action=terminate`.\", \"type\": \"string\", \"enum\": [\"success\", \"failure\"]}}, \"required\": [\"action\"], \"type\": \"object\"}}}
-</tools>
-For each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:
-<tool_call>
-{\"name\": <function-name>, \"arguments\": <args-json-object>}
-</tool_call>"
-grounding_prompt = f'''The screen's resolution is {new_width}x{new_height}.
-Point to the UI element most relevant to "{instruction}", output its coordinates using JSON format:
-```json
-[
-    {{"point_2d": [x, y], "label": "object name/description"}}
-]```'''
-trajectory_prompt = f"The user query:  {instruction}
-Task progress (You have done the following operation on the current device): "
 # Build messages
 grounding_messages = [
@@ -110,7 +74,7 @@ grounding_messages = [
     }
 ]
 trajectory_messages = [
-    {"role": "system", "content": system_prompt + tool_prompt},
     {
         "role": "user",
         "content": [
@@ -189,7 +153,8 @@ except:
 For more information, please refer to our [repo](https://github.com/Reallm-Labs/InfiGUI-R1).
----
 If you find this work useful, we would be grateful if you consider citing the following papers:
 ```bibtex
 @article{liu2025infigui,

 # Prepare inputs
 instruction = "View detailed storage space usage"
+system_prompt = 'You FIRST think about the reasoning process as an internal monologue and then provide the final answer.\nThe reasoning process MUST BE enclosed within <think> </think> tags.'
+## The following prompts are primarily sourced from https://github.com/QwenLM/Qwen2.5-VL
+tool_prompt = "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"mobile_use\", \"description\": \"Use a touchscreen to interact with a mobile device, and take screenshots.\\n* This is an interface to a mobile device with touchscreen. You can perform actions like clicking, typing, swiping, etc.\\n* Some applications may take time to start or process actions, so you may need to wait and take successive screenshots to see the results of your actions.\\n* The screen's resolution is " + str(new_width) + "x" + str(new_height) + ".\\n* Make sure to click any buttons, links, icons, etc with the cursor tip in the center of the element. Don't click boxes on their edges unless asked.\", \"parameters\": {\"properties\": {\"action\": {\"description\": \"The action to perform. The available actions are:\\n* `key`: Perform a key event on the mobile device.\\n    - This supports adb's `keyevent` syntax.\\n    - Examples: \\\"volume_up\\\", \\\"volume_down\\\", \\\"power\\\", \\\"camera\\\", \\\"clear\\\".\\n* `click`: Click the point on the screen with coordinate (x, y).\\n* `long_press`: Press the point on the screen with coordinate (x, y) for specified seconds.\\n* `swipe`: Swipe from the starting point with coordinate (x, y) to the end point with coordinates2 (x2, y2).\\n* `type`: Input the specified text into the activated input box.\\n* `system_button`: Press the system button.\\n* `open`: Open an app on the device.\\n* `wait`: Wait specified seconds for the change to happen.\\n* `terminate`: Terminate the current task and report its completion status.\", \"enum\": [\"key\", \"click\", \"long_press\", \"swipe\", \"type\", \"system_button\", \"open\", \"wait\", \"terminate\"], \"type\": \"string\"}, \"coordinate\": {\"description\": \"(x, y): The x (pixels from the left edge) and y (pixels from the top edge) coordinates to move the mouse to. Required only by `action=click`, `action=long_press`, and `action=swipe`.\", \"type\": \"array\"}, \"coordinate2\": {\"description\": \"(x, y): The x (pixels from the left edge) and y (pixels from the top edge) coordinates to move the mouse to. Required only by `action=swipe`.\", \"type\": \"array\"}, \"text\": {\"description\": \"Required only by `action=key`, `action=type`, and `action=open`.\", \"type\": \"string\"}, \"time\": {\"description\": \"The seconds to wait. Required only by `action=long_press` and `action=wait`.\", \"type\": \"number\"}, \"button\": {\"description\": \"Back means returning to the previous interface, Home means returning to the desktop, Menu means opening the application background menu, and Enter means pressing the enter. Required only by `action=system_button`\", \"enum\": [\"Back\", \"Home\", \"Menu\", \"Enter\"], \"type\": \"string\"}, \"status\": {\"description\": \"The status of the task. Required only by `action=terminate`.\", \"type\": \"string\", \"enum\": [\"success\", \"failure\"]}}, \"required\": [\"action\"], \"type\": \"object\"}}}\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>"
+grounding_prompt = f'The screen\'s resolution is {new_width}x{new_height}.\nPoint to the UI element most relevant to "{instruction}", output its coordinates using JSON format:\n```json\n[\n    {{"point_2d": [x, y], "label": "object name/description"}}\n]```'
+trajectory_prompt = f'The user query:  {instruction}\nTask progress (You have done the following operation on the current device): '
 # Build messages
 grounding_messages = [
     }
 ]
 trajectory_messages = [
+    {"role": "system", "content": system_prompt + "\n\n" + tool_prompt},
     {
         "role": "user",
         "content": [
 For more information, please refer to our [repo](https://github.com/Reallm-Labs/InfiGUI-R1).
+## Citation Information
 If you find this work useful, we would be grateful if you consider citing the following papers:
 ```bibtex
 @article{liu2025infigui,