Dataset Preview
The full dataset viewer is not available (click to read why). Only showing a preview of the rows.
The dataset generation failed
Error code: DatasetGenerationError
Exception: TypeError
Message: Couldn't cast array of type
struct<answer: string, bbox: list<item: double>, direction: string, from: list<item: double>, goal_status: string, key_comb: string, original_action_type: string, to: list<item: double>>
to
{'answer': Value('string'), 'center': List(Value('float64')), 'direction': Value('string'), 'goal_status': Value('string'), 'original_action_type': Value('string'), 'text': Value('string')}
Traceback: Traceback (most recent call last):
File "/usr/local/lib/python3.12/site-packages/datasets/builder.py", line 1831, in _prepare_split_single
writer.write_table(table)
File "/usr/local/lib/python3.12/site-packages/datasets/arrow_writer.py", line 714, in write_table
pa_table = table_cast(pa_table, self._schema)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/datasets/table.py", line 2272, in table_cast
return cast_table_to_schema(table, schema)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/datasets/table.py", line 2224, in cast_table_to_schema
cast_array_to_feature(
File "/usr/local/lib/python3.12/site-packages/datasets/table.py", line 1795, in wrapper
return pa.chunked_array([func(chunk, *args, **kwargs) for chunk in array.chunks])
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/datasets/table.py", line 2092, in cast_array_to_feature
raise TypeError(f"Couldn't cast array of type\n{_short_str(array.type)}\nto\n{_short_str(feature)}")
TypeError: Couldn't cast array of type
struct<answer: string, bbox: list<item: double>, direction: string, from: list<item: double>, goal_status: string, key_comb: string, original_action_type: string, to: list<item: double>>
to
{'answer': Value('string'), 'center': List(Value('float64')), 'direction': Value('string'), 'goal_status': Value('string'), 'original_action_type': Value('string'), 'text': Value('string')}
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "/src/services/worker/src/worker/job_runners/config/parquet_and_info.py", line 1339, in compute_config_parquet_and_info_response
parquet_operations = convert_to_parquet(builder)
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/src/services/worker/src/worker/job_runners/config/parquet_and_info.py", line 972, in convert_to_parquet
builder.download_and_prepare(
File "/usr/local/lib/python3.12/site-packages/datasets/builder.py", line 894, in download_and_prepare
self._download_and_prepare(
File "/usr/local/lib/python3.12/site-packages/datasets/builder.py", line 970, in _download_and_prepare
self._prepare_split(split_generator, **prepare_split_kwargs)
File "/usr/local/lib/python3.12/site-packages/datasets/builder.py", line 1702, in _prepare_split
for job_id, done, content in self._prepare_split_single(
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/datasets/builder.py", line 1858, in _prepare_split_single
raise DatasetGenerationError("An error occurred while generating the dataset") from e
datasets.exceptions.DatasetGenerationError: An error occurred while generating the datasetNeed help to make the dataset viewer work? Make sure to review how to configure the dataset viewer, and open a discussion for direct support.
id
string | conversations
list | task
string | action_type
string | task_attr
dict | history
list | step_instruction
string | action_refexp
string | image
string | step_info
dict | wxh
string | device
string |
|---|---|---|---|---|---|---|---|---|---|---|---|
autogui_GUIAct-smartphone_planning_10270193012375700035-00
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: What is the capital of Brazil?\nAction history: None\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Touch a task-related element<|object_ref_end|>\n{\"action_type\": \"click\", \"target\": (503,981)}"
}
] |
What is the capital of Brazil?
|
click
|
{
"answer": null,
"center": [
0.503,
0.981
],
"direction": null,
"goal_status": null,
"original_action_type": "tap",
"text": null
}
|
[] |
Touch a task-related element
|
Touch a task-related element
|
GUICourse/GUIAct/imgs/uid_episode_10270193012375700035_step_00.png
|
{
"action_type": "click",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": null,
"start": null,
"step_idx": 0,
"target": [
503,
981
],
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_10270193012375700035-01
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: What is the capital of Brazil?\nAction history: Step 1. Touch a task-related element.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Touch a task-related element<|object_ref_end|>\n{\"action_type\": \"click\", \"target\": (576,806)}"
}
] |
What is the capital of Brazil?
|
click
|
{
"answer": null,
"center": [
0.5760000000000001,
0.806
],
"direction": null,
"goal_status": null,
"original_action_type": "tap",
"text": null
}
|
[
"Touch a task-related element"
] |
Touch a task-related element
|
Touch a task-related element
|
GUICourse/GUIAct/imgs/uid_episode_10270193012375700035_step_01.png
|
{
"action_type": "click",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": null,
"start": null,
"step_idx": 1,
"target": [
576,
806
],
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_10270193012375700035-02
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: What is the capital of Brazil?\nAction history: Step 1. Touch a task-related element.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Touch a task-related element<|object_ref_end|>\n{\"action_type\": \"click\", \"target\": (662,808)}"
}
] |
What is the capital of Brazil?
|
click
|
{
"answer": null,
"center": [
0.662,
0.808
],
"direction": null,
"goal_status": null,
"original_action_type": "tap",
"text": null
}
|
[
"Touch a task-related element",
"Touch a task-related element"
] |
Touch a task-related element
|
Touch a task-related element
|
GUICourse/GUIAct/imgs/uid_episode_10270193012375700035_step_02.png
|
{
"action_type": "click",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": null,
"start": null,
"step_idx": 2,
"target": [
662,
808
],
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_10270193012375700035-03
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: What is the capital of Brazil?\nAction history: Step 1. Touch a task-related element.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Press on a task-related element<|object_ref_end|>\n{\"action_type\": \"click\", \"target\": (931,62)}"
}
] |
What is the capital of Brazil?
|
click
|
{
"answer": null,
"center": [
0.931,
0.062
],
"direction": null,
"goal_status": null,
"original_action_type": "tap",
"text": null
}
|
[
"Touch a task-related element",
"Touch a task-related element",
"Touch a task-related element"
] |
Press on a task-related element
|
Press on a task-related element
|
GUICourse/GUIAct/imgs/uid_episode_10270193012375700035_step_03.png
|
{
"action_type": "click",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": null,
"start": null,
"step_idx": 3,
"target": [
931,
62
],
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_10270193012375700035-04
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: What is the capital of Brazil?\nAction history: Step 1. Touch a task-related element. Step 2. Press on a task-related element.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Swipe left to uncover more content<|object_ref_end|>\n{\"action_type\": \"swipe\", \"start\": (950,992), \"direction\": \"left\", \"distance\": \"short\"}"
}
] |
What is the capital of Brazil?
|
swipe
|
{
"answer": null,
"center": null,
"direction": "left",
"goal_status": null,
"original_action_type": "swipe",
"text": null
}
|
[
"Touch a task-related element",
"Touch a task-related element",
"Touch a task-related element",
"Press on a task-related element"
] |
Swipe left to uncover more content
|
Swipe left to uncover more content
|
GUICourse/GUIAct/imgs/uid_episode_10270193012375700035_step_04.png
|
{
"action_type": "swipe",
"answer": null,
"direction": "left",
"distance": "short",
"goal_status": null,
"key": null,
"start": [
950,
992
],
"step_idx": 4,
"target": null,
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_10270193012375700035-05
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: What is the capital of Brazil?\nAction history: Step 1. Touch a task-related element. Step 2. Press on a task-related element. Step 3. Swipe left to uncover more content.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Fill \"What is the capital of Brazil?\" in the text box<|object_ref_end|>\n{\"action_type\": \"input_text\", \"text\": \"What is the capital of Brazil?\"}"
}
] |
What is the capital of Brazil?
|
input_text
|
{
"answer": null,
"center": null,
"direction": null,
"goal_status": null,
"original_action_type": "input",
"text": "What is the capital of Brazil?"
}
|
[
"Touch a task-related element",
"Touch a task-related element",
"Touch a task-related element",
"Press on a task-related element",
"Swipe left to uncover more content"
] |
Fill "What is the capital of Brazil?" in the text box
|
Fill "What is the capital of Brazil?" in the text box
|
GUICourse/GUIAct/imgs/uid_episode_10270193012375700035_step_05.png
|
{
"action_type": "input_text",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": null,
"start": null,
"step_idx": 5,
"target": null,
"text": "What is the capital of Brazil?"
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_10270193012375700035-06
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: What is the capital of Brazil?\nAction history: Step 1. Touch a task-related element. Step 2. Press on a task-related element. Step 3. Swipe left to uncover more content. Step 4. Fill \"What is the capital of Brazil?\" in the text box.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Press the Enter key to submit<|object_ref_end|>\n{\"action_type\": \"press_key\", \"key\": \"Enter\"}"
}
] |
What is the capital of Brazil?
|
press_key
|
{
"answer": null,
"center": null,
"direction": null,
"goal_status": null,
"original_action_type": "enter",
"text": null
}
|
[
"Touch a task-related element",
"Touch a task-related element",
"Touch a task-related element",
"Press on a task-related element",
"Swipe left to uncover more content",
"Fill \"What is the capital of Brazil?\" in the text box"
] |
Press the Enter key to submit.
|
Press the Enter key to submit
|
GUICourse/GUIAct/imgs/uid_episode_10270193012375700035_step_06.png
|
{
"action_type": "press_key",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": "Enter",
"start": null,
"step_idx": 6,
"target": null,
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_10270193012375700035-07
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: What is the capital of Brazil?\nAction history: Step 1. Touch a task-related element. Step 2. Press on a task-related element. Step 3. Swipe left to uncover more content. Step 4. Fill \"What is the capital of Brazil?\" in the text box. Step 5. Press the Enter key to submit.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>We have successfully finished the task<|object_ref_end|>\n{\"action_type\": \"status\", \"goal_status\": \"successful\", \"answer\": \"\"}"
}
] |
What is the capital of Brazil?
|
status
|
{
"answer": "",
"center": null,
"direction": null,
"goal_status": "successful",
"original_action_type": "answer",
"text": null
}
|
[
"Touch a task-related element",
"Touch a task-related element",
"Touch a task-related element",
"Press on a task-related element",
"Swipe left to uncover more content",
"Fill \"What is the capital of Brazil?\" in the text box",
"Press the Enter key to submit."
] |
We have successfully finished the task.
|
We have successfully finished the task
|
GUICourse/GUIAct/imgs/uid_episode_10270193012375700035_step_07.png
|
{
"action_type": "status",
"answer": "",
"direction": null,
"distance": null,
"goal_status": "successful",
"key": null,
"start": null,
"step_idx": 7,
"target": null,
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_12349968890740372824-00
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: What's the time in San Francisco?\nAction history: None\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Tap on a task-related element<|object_ref_end|>\n{\"action_type\": \"click\", \"target\": (503,981)}"
}
] |
What's the time in San Francisco?
|
click
|
{
"answer": null,
"center": [
0.503,
0.981
],
"direction": null,
"goal_status": null,
"original_action_type": "tap",
"text": null
}
|
[] |
Tap on a task-related element
|
Tap on a task-related element
|
GUICourse/GUIAct/imgs/uid_episode_12349968890740372824_step_00.png
|
{
"action_type": "click",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": null,
"start": null,
"step_idx": 0,
"target": [
503,
981
],
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_12349968890740372824-01
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: What's the time in San Francisco?\nAction history: Step 1. Tap on a task-related element.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Swipe up to access the target element<|object_ref_end|>\n{\"action_type\": \"swipe\", \"start\": (568,872), \"direction\": \"up\", \"distance\": \"long\"}"
}
] |
What's the time in San Francisco?
|
swipe
|
{
"answer": null,
"center": null,
"direction": "up",
"goal_status": null,
"original_action_type": "swipe",
"text": null
}
|
[
"Tap on a task-related element"
] |
Swipe up to access the target element
|
Swipe up to access the target element
|
GUICourse/GUIAct/imgs/uid_episode_12349968890740372824_step_01.png
|
{
"action_type": "swipe",
"answer": null,
"direction": "up",
"distance": "long",
"goal_status": null,
"key": null,
"start": [
568,
872
],
"step_idx": 1,
"target": null,
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_12349968890740372824-02
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: What's the time in San Francisco?\nAction history: Step 1. Tap on a task-related element. Step 2. Swipe up to access the target element.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Touch a task-related element<|object_ref_end|>\n{\"action_type\": \"click\", \"target\": (496,360)}"
}
] |
What's the time in San Francisco?
|
click
|
{
"answer": null,
"center": [
0.496,
0.36
],
"direction": null,
"goal_status": null,
"original_action_type": "tap",
"text": null
}
|
[
"Tap on a task-related element",
"Swipe up to access the target element"
] |
Touch a task-related element
|
Touch a task-related element
|
GUICourse/GUIAct/imgs/uid_episode_12349968890740372824_step_02.png
|
{
"action_type": "click",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": null,
"start": null,
"step_idx": 2,
"target": [
496,
360
],
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_12349968890740372824-03
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: What's the time in San Francisco?\nAction history: Step 1. Tap on a task-related element. Step 2. Swipe up to access the target element. Step 3. Touch a task-related element.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Hit a task-related element<|object_ref_end|>\n{\"action_type\": \"click\", \"target\": (950,112)}"
}
] |
What's the time in San Francisco?
|
click
|
{
"answer": null,
"center": [
0.9500000000000001,
0.112
],
"direction": null,
"goal_status": null,
"original_action_type": "tap",
"text": null
}
|
[
"Tap on a task-related element",
"Swipe up to access the target element",
"Touch a task-related element"
] |
Hit a task-related element
|
Hit a task-related element
|
GUICourse/GUIAct/imgs/uid_episode_12349968890740372824_step_03.png
|
{
"action_type": "click",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": null,
"start": null,
"step_idx": 3,
"target": [
950,
112
],
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_12349968890740372824-04
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: What's the time in San Francisco?\nAction history: Step 1. Tap on a task-related element. Step 2. Swipe up to access the target element. Step 3. Touch a task-related element. Step 4. Hit a task-related element.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Enter text \"What's the time in San Francisco?\" in the text box<|object_ref_end|>\n{\"action_type\": \"input_text\", \"text\": \"What's the time in San Francisco?\"}"
}
] |
What's the time in San Francisco?
|
input_text
|
{
"answer": null,
"center": null,
"direction": null,
"goal_status": null,
"original_action_type": "input",
"text": "What's the time in San Francisco?"
}
|
[
"Tap on a task-related element",
"Swipe up to access the target element",
"Touch a task-related element",
"Hit a task-related element"
] |
Enter text "What's the time in San Francisco?" in the text box
|
Enter text "What's the time in San Francisco?" in the text box
|
GUICourse/GUIAct/imgs/uid_episode_12349968890740372824_step_04.png
|
{
"action_type": "input_text",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": null,
"start": null,
"step_idx": 4,
"target": null,
"text": "What's the time in San Francisco?"
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_12349968890740372824-05
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: What's the time in San Francisco?\nAction history: Step 1. Tap on a task-related element. Step 2. Swipe up to access the target element. Step 3. Touch a task-related element. Step 4. Hit a task-related element. Step 5. Enter text \"What's the time in San Francisco?\" in the text box.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>We have successfully finished the task<|object_ref_end|>\n{\"action_type\": \"status\", \"goal_status\": \"successful\", \"answer\": \"\"}"
}
] |
What's the time in San Francisco?
|
status
|
{
"answer": "",
"center": null,
"direction": null,
"goal_status": "successful",
"original_action_type": "answer",
"text": null
}
|
[
"Tap on a task-related element",
"Swipe up to access the target element",
"Touch a task-related element",
"Hit a task-related element",
"Enter text \"What's the time in San Francisco?\" in the text box"
] |
We have successfully finished the task.
|
We have successfully finished the task
|
GUICourse/GUIAct/imgs/uid_episode_12349968890740372824_step_05.png
|
{
"action_type": "status",
"answer": "",
"direction": null,
"distance": null,
"goal_status": "successful",
"key": null,
"start": null,
"step_idx": 5,
"target": null,
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_1494430438008457652-00
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: Search for a new eyeshadow on Sephora\nAction history: None\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Click on a task-related element<|object_ref_end|>\n{\"action_type\": \"click\", \"target\": (697,792)}"
}
] |
Search for a new eyeshadow on Sephora
|
click
|
{
"answer": null,
"center": [
0.6970000000000001,
0.792
],
"direction": null,
"goal_status": null,
"original_action_type": "tap",
"text": null
}
|
[] |
Click on a task-related element
|
Click on a task-related element
|
GUICourse/GUIAct/imgs/uid_episode_1494430438008457652_step_00.png
|
{
"action_type": "click",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": null,
"start": null,
"step_idx": 0,
"target": [
697,
792
],
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_1494430438008457652-01
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: Search for a new eyeshadow on Sephora\nAction history: Step 1. Click on a task-related element.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Press on a task-related element<|object_ref_end|>\n{\"action_type\": \"click\", \"target\": (724,781)}"
}
] |
Search for a new eyeshadow on Sephora
|
click
|
{
"answer": null,
"center": [
0.724,
0.781
],
"direction": null,
"goal_status": null,
"original_action_type": "tap",
"text": null
}
|
[
"Click on a task-related element"
] |
Press on a task-related element
|
Press on a task-related element
|
GUICourse/GUIAct/imgs/uid_episode_1494430438008457652_step_01.png
|
{
"action_type": "click",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": null,
"start": null,
"step_idx": 1,
"target": [
724,
781
],
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_1494430438008457652-02
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: Search for a new eyeshadow on Sephora\nAction history: Step 1. Click on a task-related element. Step 2. Press on a task-related element.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Click on a task-related element<|object_ref_end|>\n{\"action_type\": \"click\", \"target\": (724,781)}"
}
] |
Search for a new eyeshadow on Sephora
|
click
|
{
"answer": null,
"center": [
0.724,
0.781
],
"direction": null,
"goal_status": null,
"original_action_type": "tap",
"text": null
}
|
[
"Click on a task-related element",
"Press on a task-related element"
] |
Click on a task-related element
|
Click on a task-related element
|
GUICourse/GUIAct/imgs/uid_episode_1494430438008457652_step_02.png
|
{
"action_type": "click",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": null,
"start": null,
"step_idx": 2,
"target": [
724,
781
],
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_1494430438008457652-03
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: Search for a new eyeshadow on Sephora\nAction history: Step 1. Click on a task-related element. Step 2. Press on a task-related element. Step 3. Click on a task-related element.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Press on a task-related element<|object_ref_end|>\n{\"action_type\": \"click\", \"target\": (724,781)}"
}
] |
Search for a new eyeshadow on Sephora
|
click
|
{
"answer": null,
"center": [
0.724,
0.781
],
"direction": null,
"goal_status": null,
"original_action_type": "tap",
"text": null
}
|
[
"Click on a task-related element",
"Press on a task-related element",
"Click on a task-related element"
] |
Press on a task-related element
|
Press on a task-related element
|
GUICourse/GUIAct/imgs/uid_episode_1494430438008457652_step_03.png
|
{
"action_type": "click",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": null,
"start": null,
"step_idx": 3,
"target": [
724,
781
],
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_1494430438008457652-04
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: Search for a new eyeshadow on Sephora\nAction history: Step 1. Click on a task-related element. Step 2. Press on a task-related element. Step 3. Click on a task-related element. Step 4. Press on a task-related element.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Tap on a task-related element<|object_ref_end|>\n{\"action_type\": \"click\", \"target\": (674,790)}"
}
] |
Search for a new eyeshadow on Sephora
|
click
|
{
"answer": null,
"center": [
0.674,
0.79
],
"direction": null,
"goal_status": null,
"original_action_type": "tap",
"text": null
}
|
[
"Click on a task-related element",
"Press on a task-related element",
"Click on a task-related element",
"Press on a task-related element"
] |
Tap on a task-related element
|
Tap on a task-related element
|
GUICourse/GUIAct/imgs/uid_episode_1494430438008457652_step_04.png
|
{
"action_type": "click",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": null,
"start": null,
"step_idx": 4,
"target": [
674,
790
],
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_1494430438008457652-05
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: Search for a new eyeshadow on Sephora\nAction history: Step 1. Click on a task-related element. Step 2. Press on a task-related element. Step 3. Click on a task-related element. Step 4. Press on a task-related element. Step 5. Tap on a task-related element.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Tap on a task-related element<|object_ref_end|>\n{\"action_type\": \"click\", \"target\": (929,120)}"
}
] |
Search for a new eyeshadow on Sephora
|
click
|
{
"answer": null,
"center": [
0.929,
0.12
],
"direction": null,
"goal_status": null,
"original_action_type": "tap",
"text": null
}
|
[
"Click on a task-related element",
"Press on a task-related element",
"Click on a task-related element",
"Press on a task-related element",
"Tap on a task-related element"
] |
Tap on a task-related element
|
Tap on a task-related element
|
GUICourse/GUIAct/imgs/uid_episode_1494430438008457652_step_05.png
|
{
"action_type": "click",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": null,
"start": null,
"step_idx": 5,
"target": [
929,
120
],
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_1494430438008457652-06
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: Search for a new eyeshadow on Sephora\nAction history: Step 1. Click on a task-related element. Step 2. Press on a task-related element. Step 3. Click on a task-related element. Step 4. Press on a task-related element. Step 5. Tap on a task-related element.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Fill \"new eyeshadow on Sephora\" in the text box<|object_ref_end|>\n{\"action_type\": \"input_text\", \"text\": \"new eyeshadow on Sephora\"}"
}
] |
Search for a new eyeshadow on Sephora
|
input_text
|
{
"answer": null,
"center": null,
"direction": null,
"goal_status": null,
"original_action_type": "input",
"text": "new eyeshadow on Sephora"
}
|
[
"Click on a task-related element",
"Press on a task-related element",
"Click on a task-related element",
"Press on a task-related element",
"Tap on a task-related element",
"Tap on a task-related element"
] |
Fill "new eyeshadow on Sephora" in the text box
|
Fill "new eyeshadow on Sephora" in the text box
|
GUICourse/GUIAct/imgs/uid_episode_1494430438008457652_step_06.png
|
{
"action_type": "input_text",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": null,
"start": null,
"step_idx": 6,
"target": null,
"text": "new eyeshadow on Sephora"
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_1494430438008457652-07
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: Search for a new eyeshadow on Sephora\nAction history: Step 1. Click on a task-related element. Step 2. Press on a task-related element. Step 3. Click on a task-related element. Step 4. Press on a task-related element. Step 5. Tap on a task-related element. Step 6. Fill \"new eyeshadow on Sephora\" in the text box.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Tap the Enter key to confirm the input<|object_ref_end|>\n{\"action_type\": \"press_key\", \"key\": \"Enter\"}"
}
] |
Search for a new eyeshadow on Sephora
|
press_key
|
{
"answer": null,
"center": null,
"direction": null,
"goal_status": null,
"original_action_type": "enter",
"text": null
}
|
[
"Click on a task-related element",
"Press on a task-related element",
"Click on a task-related element",
"Press on a task-related element",
"Tap on a task-related element",
"Tap on a task-related element",
"Fill \"new eyeshadow on Sephora\" in the text box"
] |
Tap the Enter key to confirm the input.
|
Tap the Enter key to confirm the input
|
GUICourse/GUIAct/imgs/uid_episode_1494430438008457652_step_07.png
|
{
"action_type": "press_key",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": "Enter",
"start": null,
"step_idx": 7,
"target": null,
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_1494430438008457652-08
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: Search for a new eyeshadow on Sephora\nAction history: Step 2. Press on a task-related element. Step 3. Click on a task-related element. Step 4. Press on a task-related element. Step 5. Tap on a task-related element. Step 6. Fill \"new eyeshadow on Sephora\" in the text box. Step 7. Tap the Enter key to confirm the input.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>We have successfully finished the task<|object_ref_end|>\n{\"action_type\": \"status\", \"goal_status\": \"successful\", \"answer\": \"\"}"
}
] |
Search for a new eyeshadow on Sephora
|
status
|
{
"answer": "",
"center": null,
"direction": null,
"goal_status": "successful",
"original_action_type": "answer",
"text": null
}
|
[
"Click on a task-related element",
"Press on a task-related element",
"Click on a task-related element",
"Press on a task-related element",
"Tap on a task-related element",
"Tap on a task-related element",
"Fill \"new eyeshadow on Sephora\" in the text box",
"Tap the Enter key to confirm the input."
] |
We have successfully finished the task.
|
We have successfully finished the task
|
GUICourse/GUIAct/imgs/uid_episode_1494430438008457652_step_08.png
|
{
"action_type": "status",
"answer": "",
"direction": null,
"distance": null,
"goal_status": "successful",
"key": null,
"start": null,
"step_idx": 8,
"target": null,
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_12124002721988046403-00
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: What is the speed of a jet?\nAction history: None\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Hit a task-related element<|object_ref_end|>\n{\"action_type\": \"click\", \"target\": (503,981)}"
}
] |
What is the speed of a jet?
|
click
|
{
"answer": null,
"center": [
0.503,
0.981
],
"direction": null,
"goal_status": null,
"original_action_type": "tap",
"text": null
}
|
[] |
Hit a task-related element
|
Hit a task-related element
|
GUICourse/GUIAct/imgs/uid_episode_12124002721988046403_step_00.png
|
{
"action_type": "click",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": null,
"start": null,
"step_idx": 0,
"target": [
503,
981
],
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_12124002721988046403-01
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: What is the speed of a jet?\nAction history: Step 1. Hit a task-related element.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Touch a task-related element<|object_ref_end|>\n{\"action_type\": \"click\", \"target\": (669,786)}"
}
] |
What is the speed of a jet?
|
click
|
{
"answer": null,
"center": [
0.669,
0.786
],
"direction": null,
"goal_status": null,
"original_action_type": "tap",
"text": null
}
|
[
"Hit a task-related element"
] |
Touch a task-related element
|
Touch a task-related element
|
GUICourse/GUIAct/imgs/uid_episode_12124002721988046403_step_01.png
|
{
"action_type": "click",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": null,
"start": null,
"step_idx": 1,
"target": [
669,
786
],
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_12124002721988046403-02
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: What is the speed of a jet?\nAction history: Step 1. Hit a task-related element. Step 2. Touch a task-related element.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Press on a task-related element<|object_ref_end|>\n{\"action_type\": \"click\", \"target\": (722,176)}"
}
] |
What is the speed of a jet?
|
click
|
{
"answer": null,
"center": [
0.722,
0.176
],
"direction": null,
"goal_status": null,
"original_action_type": "tap",
"text": null
}
|
[
"Hit a task-related element",
"Touch a task-related element"
] |
Press on a task-related element
|
Press on a task-related element
|
GUICourse/GUIAct/imgs/uid_episode_12124002721988046403_step_02.png
|
{
"action_type": "click",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": null,
"start": null,
"step_idx": 2,
"target": [
722,
176
],
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_12124002721988046403-03
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: What is the speed of a jet?\nAction history: Step 1. Hit a task-related element. Step 2. Touch a task-related element. Step 3. Press on a task-related element.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Press on a task-related element<|object_ref_end|>\n{\"action_type\": \"click\", \"target\": (932,124)}"
}
] |
What is the speed of a jet?
|
click
|
{
"answer": null,
"center": [
0.932,
0.124
],
"direction": null,
"goal_status": null,
"original_action_type": "tap",
"text": null
}
|
[
"Hit a task-related element",
"Touch a task-related element",
"Press on a task-related element"
] |
Press on a task-related element
|
Press on a task-related element
|
GUICourse/GUIAct/imgs/uid_episode_12124002721988046403_step_03.png
|
{
"action_type": "click",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": null,
"start": null,
"step_idx": 3,
"target": [
932,
124
],
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_12124002721988046403-04
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: What is the speed of a jet?\nAction history: Step 1. Hit a task-related element. Step 2. Touch a task-related element. Step 3. Press on a task-related element.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Swipe right to locate the desired target<|object_ref_end|>\n{\"action_type\": \"swipe\", \"start\": (731,999), \"direction\": \"right\", \"distance\": \"short\"}"
}
] |
What is the speed of a jet?
|
swipe
|
{
"answer": null,
"center": null,
"direction": "right",
"goal_status": null,
"original_action_type": "swipe",
"text": null
}
|
[
"Hit a task-related element",
"Touch a task-related element",
"Press on a task-related element",
"Press on a task-related element"
] |
Swipe right to locate the desired target
|
Swipe right to locate the desired target
|
GUICourse/GUIAct/imgs/uid_episode_12124002721988046403_step_04.png
|
{
"action_type": "swipe",
"answer": null,
"direction": "right",
"distance": "short",
"goal_status": null,
"key": null,
"start": [
731,
999
],
"step_idx": 4,
"target": null,
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_12124002721988046403-05
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: What is the speed of a jet?\nAction history: Step 1. Hit a task-related element. Step 2. Touch a task-related element. Step 3. Press on a task-related element. Step 4. Swipe right to locate the desired target.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Fill \"What is the speed of a jet?\" in the text box<|object_ref_end|>\n{\"action_type\": \"input_text\", \"text\": \"What is the speed of a jet?\"}"
}
] |
What is the speed of a jet?
|
input_text
|
{
"answer": null,
"center": null,
"direction": null,
"goal_status": null,
"original_action_type": "input",
"text": "What is the speed of a jet?"
}
|
[
"Hit a task-related element",
"Touch a task-related element",
"Press on a task-related element",
"Press on a task-related element",
"Swipe right to locate the desired target"
] |
Fill "What is the speed of a jet?" in the text box
|
Fill "What is the speed of a jet?" in the text box
|
GUICourse/GUIAct/imgs/uid_episode_12124002721988046403_step_05.png
|
{
"action_type": "input_text",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": null,
"start": null,
"step_idx": 5,
"target": null,
"text": "What is the speed of a jet?"
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_12124002721988046403-06
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: What is the speed of a jet?\nAction history: Step 1. Hit a task-related element. Step 2. Touch a task-related element. Step 3. Press on a task-related element. Step 4. Swipe right to locate the desired target. Step 5. Fill \"What is the speed of a jet?\" in the text box.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Tap the Enter key to submit<|object_ref_end|>\n{\"action_type\": \"press_key\", \"key\": \"Enter\"}"
}
] |
What is the speed of a jet?
|
press_key
|
{
"answer": null,
"center": null,
"direction": null,
"goal_status": null,
"original_action_type": "enter",
"text": null
}
|
[
"Hit a task-related element",
"Touch a task-related element",
"Press on a task-related element",
"Press on a task-related element",
"Swipe right to locate the desired target",
"Fill \"What is the speed of a jet?\" in the text box"
] |
Tap the Enter key to submit.
|
Tap the Enter key to submit
|
GUICourse/GUIAct/imgs/uid_episode_12124002721988046403_step_06.png
|
{
"action_type": "press_key",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": "Enter",
"start": null,
"step_idx": 6,
"target": null,
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_12124002721988046403-07
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: What is the speed of a jet?\nAction history: Step 1. Hit a task-related element. Step 2. Touch a task-related element. Step 3. Press on a task-related element. Step 4. Swipe right to locate the desired target. Step 5. Fill \"What is the speed of a jet?\" in the text box. Step 6. Tap the Enter key to submit.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>We have successfully finished the task<|object_ref_end|>\n{\"action_type\": \"status\", \"goal_status\": \"successful\", \"answer\": \"\"}"
}
] |
What is the speed of a jet?
|
status
|
{
"answer": "",
"center": null,
"direction": null,
"goal_status": "successful",
"original_action_type": "answer",
"text": null
}
|
[
"Hit a task-related element",
"Touch a task-related element",
"Press on a task-related element",
"Press on a task-related element",
"Swipe right to locate the desired target",
"Fill \"What is the speed of a jet?\" in the text box",
"Tap the Enter key to submit."
] |
We have successfully finished the task.
|
We have successfully finished the task
|
GUICourse/GUIAct/imgs/uid_episode_12124002721988046403_step_07.png
|
{
"action_type": "status",
"answer": "",
"direction": null,
"distance": null,
"goal_status": "successful",
"key": null,
"start": null,
"step_idx": 7,
"target": null,
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_3470007673985222275-00
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: What's the weather like in Mexico City?\nAction history: None\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Swipe up to uncover more content<|object_ref_end|>\n{\"action_type\": \"swipe\", \"start\": (424,867), \"direction\": \"up\", \"distance\": \"long\"}"
}
] |
What's the weather like in Mexico City?
|
swipe
|
{
"answer": null,
"center": null,
"direction": "up",
"goal_status": null,
"original_action_type": "swipe",
"text": null
}
|
[] |
Swipe up to uncover more content
|
Swipe up to uncover more content
|
GUICourse/GUIAct/imgs/uid_episode_3470007673985222275_step_00.png
|
{
"action_type": "swipe",
"answer": null,
"direction": "up",
"distance": "long",
"goal_status": null,
"key": null,
"start": [
424,
867
],
"step_idx": 0,
"target": null,
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_3470007673985222275-01
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: What's the weather like in Mexico City?\nAction history: Step 1. Swipe up to uncover more content.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Tap on a task-related element<|object_ref_end|>\n{\"action_type\": \"click\", \"target\": (496,367)}"
}
] |
What's the weather like in Mexico City?
|
click
|
{
"answer": null,
"center": [
0.496,
0.367
],
"direction": null,
"goal_status": null,
"original_action_type": "tap",
"text": null
}
|
[
"Swipe up to uncover more content"
] |
Tap on a task-related element
|
Tap on a task-related element
|
GUICourse/GUIAct/imgs/uid_episode_3470007673985222275_step_01.png
|
{
"action_type": "click",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": null,
"start": null,
"step_idx": 1,
"target": [
496,
367
],
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_3470007673985222275-02
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: What's the weather like in Mexico City?\nAction history: Step 1. Swipe up to uncover more content. Step 2. Tap on a task-related element.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Click on a task-related element<|object_ref_end|>\n{\"action_type\": \"click\", \"target\": (722,171)}"
}
] |
What's the weather like in Mexico City?
|
click
|
{
"answer": null,
"center": [
0.722,
0.171
],
"direction": null,
"goal_status": null,
"original_action_type": "tap",
"text": null
}
|
[
"Swipe up to uncover more content",
"Tap on a task-related element"
] |
Click on a task-related element
|
Click on a task-related element
|
GUICourse/GUIAct/imgs/uid_episode_3470007673985222275_step_02.png
|
{
"action_type": "click",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": null,
"start": null,
"step_idx": 2,
"target": [
722,
171
],
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_3470007673985222275-03
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: What's the weather like in Mexico City?\nAction history: Step 1. Swipe up to uncover more content. Step 2. Tap on a task-related element. Step 3. Click on a task-related element.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Hit a task-related element<|object_ref_end|>\n{\"action_type\": \"click\", \"target\": (929,121)}"
}
] |
What's the weather like in Mexico City?
|
click
|
{
"answer": null,
"center": [
0.929,
0.121
],
"direction": null,
"goal_status": null,
"original_action_type": "tap",
"text": null
}
|
[
"Swipe up to uncover more content",
"Tap on a task-related element",
"Click on a task-related element"
] |
Hit a task-related element
|
Hit a task-related element
|
GUICourse/GUIAct/imgs/uid_episode_3470007673985222275_step_03.png
|
{
"action_type": "click",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": null,
"start": null,
"step_idx": 3,
"target": [
929,
121
],
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_3470007673985222275-04
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: What's the weather like in Mexico City?\nAction history: Step 1. Swipe up to uncover more content. Step 2. Tap on a task-related element. Step 3. Click on a task-related element. Step 4. Hit a task-related element.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Type \"What's the weather like in Mexico City?\" into the text box<|object_ref_end|>\n{\"action_type\": \"input_text\", \"text\": \"What's the weather like in Mexico City?\"}"
}
] |
What's the weather like in Mexico City?
|
input_text
|
{
"answer": null,
"center": null,
"direction": null,
"goal_status": null,
"original_action_type": "input",
"text": "What's the weather like in Mexico City?"
}
|
[
"Swipe up to uncover more content",
"Tap on a task-related element",
"Click on a task-related element",
"Hit a task-related element"
] |
Type "What's the weather like in Mexico City?" into the text box
|
Type "What's the weather like in Mexico City?" into the text box
|
GUICourse/GUIAct/imgs/uid_episode_3470007673985222275_step_04.png
|
{
"action_type": "input_text",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": null,
"start": null,
"step_idx": 4,
"target": null,
"text": "What's the weather like in Mexico City?"
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_3470007673985222275-05
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: What's the weather like in Mexico City?\nAction history: Step 1. Swipe up to uncover more content. Step 2. Tap on a task-related element. Step 3. Click on a task-related element. Step 4. Hit a task-related element. Step 5. Type \"What's the weather like in Mexico City?\" into the text box.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Press the Enter key to submit<|object_ref_end|>\n{\"action_type\": \"press_key\", \"key\": \"Enter\"}"
}
] |
What's the weather like in Mexico City?
|
press_key
|
{
"answer": null,
"center": null,
"direction": null,
"goal_status": null,
"original_action_type": "enter",
"text": null
}
|
[
"Swipe up to uncover more content",
"Tap on a task-related element",
"Click on a task-related element",
"Hit a task-related element",
"Type \"What's the weather like in Mexico City?\" into the text box"
] |
Press the Enter key to submit.
|
Press the Enter key to submit
|
GUICourse/GUIAct/imgs/uid_episode_3470007673985222275_step_05.png
|
{
"action_type": "press_key",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": "Enter",
"start": null,
"step_idx": 5,
"target": null,
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_3470007673985222275-06
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: What's the weather like in Mexico City?\nAction history: Step 1. Swipe up to uncover more content. Step 2. Tap on a task-related element. Step 3. Click on a task-related element. Step 4. Hit a task-related element. Step 5. Type \"What's the weather like in Mexico City?\" into the text box. Step 6. Press the Enter key to submit.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>The task has been completed successfully<|object_ref_end|>\n{\"action_type\": \"status\", \"goal_status\": \"successful\", \"answer\": \"\"}"
}
] |
What's the weather like in Mexico City?
|
status
|
{
"answer": "",
"center": null,
"direction": null,
"goal_status": "successful",
"original_action_type": "answer",
"text": null
}
|
[
"Swipe up to uncover more content",
"Tap on a task-related element",
"Click on a task-related element",
"Hit a task-related element",
"Type \"What's the weather like in Mexico City?\" into the text box",
"Press the Enter key to submit."
] |
The task has been completed successfully.
|
The task has been completed successfully
|
GUICourse/GUIAct/imgs/uid_episode_3470007673985222275_step_06.png
|
{
"action_type": "status",
"answer": "",
"direction": null,
"distance": null,
"goal_status": "successful",
"key": null,
"start": null,
"step_idx": 6,
"target": null,
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_945903758176282501-00
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: Find a good burger place on Maps\nAction history: None\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Click on a task-related element<|object_ref_end|>\n{\"action_type\": \"click\", \"target\": (653,788)}"
}
] |
Find a good burger place on Maps
|
click
|
{
"answer": null,
"center": [
0.653,
0.788
],
"direction": null,
"goal_status": null,
"original_action_type": "tap",
"text": null
}
|
[] |
Click on a task-related element
|
Click on a task-related element
|
GUICourse/GUIAct/imgs/uid_episode_945903758176282501_step_00.png
|
{
"action_type": "click",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": null,
"start": null,
"step_idx": 0,
"target": [
653,
788
],
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_945903758176282501-01
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: Find a good burger place on Maps\nAction history: Step 1. Click on a task-related element.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Tap on a task-related element<|object_ref_end|>\n{\"action_type\": \"click\", \"target\": (761,192)}"
}
] |
Find a good burger place on Maps
|
click
|
{
"answer": null,
"center": [
0.761,
0.192
],
"direction": null,
"goal_status": null,
"original_action_type": "tap",
"text": null
}
|
[
"Click on a task-related element"
] |
Tap on a task-related element
|
Tap on a task-related element
|
GUICourse/GUIAct/imgs/uid_episode_945903758176282501_step_01.png
|
{
"action_type": "click",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": null,
"start": null,
"step_idx": 1,
"target": [
761,
192
],
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_945903758176282501-02
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: Find a good burger place on Maps\nAction history: Step 1. Click on a task-related element. Step 2. Tap on a task-related element.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Click on a task-related element<|object_ref_end|>\n{\"action_type\": \"click\", \"target\": (938,117)}"
}
] |
Find a good burger place on Maps
|
click
|
{
"answer": null,
"center": [
0.9380000000000001,
0.117
],
"direction": null,
"goal_status": null,
"original_action_type": "tap",
"text": null
}
|
[
"Click on a task-related element",
"Tap on a task-related element"
] |
Click on a task-related element
|
Click on a task-related element
|
GUICourse/GUIAct/imgs/uid_episode_945903758176282501_step_02.png
|
{
"action_type": "click",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": null,
"start": null,
"step_idx": 2,
"target": [
938,
117
],
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_945903758176282501-03
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: Find a good burger place on Maps\nAction history: Step 1. Click on a task-related element. Step 2. Tap on a task-related element. Step 3. Click on a task-related element.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Fill \"Find a good burger place on Maps\" in the text box<|object_ref_end|>\n{\"action_type\": \"input_text\", \"text\": \"Find a good burger place on Maps\"}"
}
] |
Find a good burger place on Maps
|
input_text
|
{
"answer": null,
"center": null,
"direction": null,
"goal_status": null,
"original_action_type": "input",
"text": "Find a good burger place on Maps"
}
|
[
"Click on a task-related element",
"Tap on a task-related element",
"Click on a task-related element"
] |
Fill "Find a good burger place on Maps" in the text box
|
Fill "Find a good burger place on Maps" in the text box
|
GUICourse/GUIAct/imgs/uid_episode_945903758176282501_step_03.png
|
{
"action_type": "input_text",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": null,
"start": null,
"step_idx": 3,
"target": null,
"text": "Find a good burger place on Maps"
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_945903758176282501-04
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: Find a good burger place on Maps\nAction history: Step 1. Click on a task-related element. Step 2. Tap on a task-related element. Step 3. Click on a task-related element. Step 4. Fill \"Find a good burger place on Maps\" in the text box.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Tap the Enter key to submit<|object_ref_end|>\n{\"action_type\": \"press_key\", \"key\": \"Enter\"}"
}
] |
Find a good burger place on Maps
|
press_key
|
{
"answer": null,
"center": null,
"direction": null,
"goal_status": null,
"original_action_type": "enter",
"text": null
}
|
[
"Click on a task-related element",
"Tap on a task-related element",
"Click on a task-related element",
"Fill \"Find a good burger place on Maps\" in the text box"
] |
Tap the Enter key to submit.
|
Tap the Enter key to submit
|
GUICourse/GUIAct/imgs/uid_episode_945903758176282501_step_04.png
|
{
"action_type": "press_key",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": "Enter",
"start": null,
"step_idx": 4,
"target": null,
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_945903758176282501-05
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: Find a good burger place on Maps\nAction history: Step 1. Click on a task-related element. Step 2. Tap on a task-related element. Step 3. Click on a task-related element. Step 4. Fill \"Find a good burger place on Maps\" in the text box. Step 5. Tap the Enter key to submit.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>The task has been completed without issues<|object_ref_end|>\n{\"action_type\": \"status\", \"goal_status\": \"successful\", \"answer\": \"\"}"
}
] |
Find a good burger place on Maps
|
status
|
{
"answer": "",
"center": null,
"direction": null,
"goal_status": "successful",
"original_action_type": "answer",
"text": null
}
|
[
"Click on a task-related element",
"Tap on a task-related element",
"Click on a task-related element",
"Fill \"Find a good burger place on Maps\" in the text box",
"Tap the Enter key to submit."
] |
The task has been completed without issues.
|
The task has been completed without issues
|
GUICourse/GUIAct/imgs/uid_episode_945903758176282501_step_05.png
|
{
"action_type": "status",
"answer": "",
"direction": null,
"distance": null,
"goal_status": "successful",
"key": null,
"start": null,
"step_idx": 5,
"target": null,
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_17872121859466277187-00
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: Open the clock\nAction history: None\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Touch a task-related element<|object_ref_end|>\n{\"action_type\": \"click\", \"target\": (503,981)}"
}
] |
Open the clock
|
click
|
{
"answer": null,
"center": [
0.503,
0.981
],
"direction": null,
"goal_status": null,
"original_action_type": "tap",
"text": null
}
|
[] |
Touch a task-related element
|
Touch a task-related element
|
GUICourse/GUIAct/imgs/uid_episode_17872121859466277187_step_00.png
|
{
"action_type": "click",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": null,
"start": null,
"step_idx": 0,
"target": [
503,
981
],
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_17872121859466277187-01
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: Open the clock\nAction history: Step 1. Touch a task-related element.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Swipe up to find the page you need<|object_ref_end|>\n{\"action_type\": \"swipe\", \"start\": (422,881), \"direction\": \"up\", \"distance\": \"long\"}"
}
] |
Open the clock
|
swipe
|
{
"answer": null,
"center": null,
"direction": "up",
"goal_status": null,
"original_action_type": "swipe",
"text": null
}
|
[
"Touch a task-related element"
] |
Swipe up to find the page you need
|
Swipe up to find the page you need
|
GUICourse/GUIAct/imgs/uid_episode_17872121859466277187_step_01.png
|
{
"action_type": "swipe",
"answer": null,
"direction": "up",
"distance": "long",
"goal_status": null,
"key": null,
"start": [
422,
881
],
"step_idx": 1,
"target": null,
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_17872121859466277187-02
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: Open the clock\nAction history: Step 1. Touch a task-related element. Step 2. Swipe up to find the page you need.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Tap on a task-related element<|object_ref_end|>\n{\"action_type\": \"click\", \"target\": (683,376)}"
}
] |
Open the clock
|
click
|
{
"answer": null,
"center": [
0.683,
0.376
],
"direction": null,
"goal_status": null,
"original_action_type": "tap",
"text": null
}
|
[
"Touch a task-related element",
"Swipe up to find the page you need"
] |
Tap on a task-related element
|
Tap on a task-related element
|
GUICourse/GUIAct/imgs/uid_episode_17872121859466277187_step_02.png
|
{
"action_type": "click",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": null,
"start": null,
"step_idx": 2,
"target": [
683,
376
],
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_17872121859466277187-03
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: Open the clock\nAction history: Step 1. Touch a task-related element. Step 2. Swipe up to find the page you need. Step 3. Tap on a task-related element.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Successfully completed the task<|object_ref_end|>\n{\"action_type\": \"status\", \"goal_status\": \"successful\", \"answer\": \"\"}"
}
] |
Open the clock
|
status
|
{
"answer": "",
"center": null,
"direction": null,
"goal_status": "successful",
"original_action_type": "answer",
"text": null
}
|
[
"Touch a task-related element",
"Swipe up to find the page you need",
"Tap on a task-related element"
] |
Successfully completed the task.
|
Successfully completed the task
|
GUICourse/GUIAct/imgs/uid_episode_17872121859466277187_step_03.png
|
{
"action_type": "status",
"answer": "",
"direction": null,
"distance": null,
"goal_status": "successful",
"key": null,
"start": null,
"step_idx": 3,
"target": null,
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_16776413361916146026-00
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: What's the news in Argentina?\nAction history: None\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Type \"news in argentina\" into the text box<|object_ref_end|>\n{\"action_type\": \"input_text\", \"text\": \"news in argentina\"}"
}
] |
What's the news in Argentina?
|
input_text
|
{
"answer": null,
"center": null,
"direction": null,
"goal_status": null,
"original_action_type": "input",
"text": "news in argentina"
}
|
[] |
Type "news in argentina" into the text box
|
Type "news in argentina" into the text box
|
GUICourse/GUIAct/imgs/uid_episode_16776413361916146026_step_00.png
|
{
"action_type": "input_text",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": null,
"start": null,
"step_idx": 0,
"target": null,
"text": "news in argentina"
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_16776413361916146026-01
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: What's the news in Argentina?\nAction history: Step 1. Type \"news in argentina\" into the text box.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Touch a task-related element<|object_ref_end|>\n{\"action_type\": \"click\", \"target\": (496,122)}"
}
] |
What's the news in Argentina?
|
click
|
{
"answer": null,
"center": [
0.496,
0.122
],
"direction": null,
"goal_status": null,
"original_action_type": "tap",
"text": null
}
|
[
"Type \"news in argentina\" into the text box"
] |
Touch a task-related element
|
Touch a task-related element
|
GUICourse/GUIAct/imgs/uid_episode_16776413361916146026_step_01.png
|
{
"action_type": "click",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": null,
"start": null,
"step_idx": 1,
"target": [
496,
122
],
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_16776413361916146026-02
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: What's the news in Argentina?\nAction history: Step 1. Type \"news in argentina\" into the text box. Step 2. Touch a task-related element.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Touch a task-related element<|object_ref_end|>\n{\"action_type\": \"click\", \"target\": (190,165)}"
}
] |
What's the news in Argentina?
|
click
|
{
"answer": null,
"center": [
0.19,
0.165
],
"direction": null,
"goal_status": null,
"original_action_type": "tap",
"text": null
}
|
[
"Type \"news in argentina\" into the text box",
"Touch a task-related element"
] |
Touch a task-related element
|
Touch a task-related element
|
GUICourse/GUIAct/imgs/uid_episode_16776413361916146026_step_02.png
|
{
"action_type": "click",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": null,
"start": null,
"step_idx": 2,
"target": [
190,
165
],
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_16776413361916146026-03
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: What's the news in Argentina?\nAction history: Step 1. Type \"news in argentina\" into the text box. Step 2. Touch a task-related element.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>The task has been completed without issues<|object_ref_end|>\n{\"action_type\": \"status\", \"goal_status\": \"successful\", \"answer\": \"\"}"
}
] |
What's the news in Argentina?
|
status
|
{
"answer": "",
"center": null,
"direction": null,
"goal_status": "successful",
"original_action_type": "answer",
"text": null
}
|
[
"Type \"news in argentina\" into the text box",
"Touch a task-related element",
"Touch a task-related element"
] |
The task has been completed without issues.
|
The task has been completed without issues
|
GUICourse/GUIAct/imgs/uid_episode_16776413361916146026_step_03.png
|
{
"action_type": "status",
"answer": "",
"direction": null,
"distance": null,
"goal_status": "successful",
"key": null,
"start": null,
"step_idx": 3,
"target": null,
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_31257933348203510-00
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: What's the time in New York?\nAction history: None\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Hit a task-related element<|object_ref_end|>\n{\"action_type\": \"click\", \"target\": (685,803)}"
}
] |
What's the time in New York?
|
click
|
{
"answer": null,
"center": [
0.685,
0.803
],
"direction": null,
"goal_status": null,
"original_action_type": "tap",
"text": null
}
|
[] |
Hit a task-related element
|
Hit a task-related element
|
GUICourse/GUIAct/imgs/uid_episode_31257933348203510_step_00.png
|
{
"action_type": "click",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": null,
"start": null,
"step_idx": 0,
"target": [
685,
803
],
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_31257933348203510-01
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: What's the time in New York?\nAction history: Step 1. Hit a task-related element.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Press on a task-related element<|object_ref_end|>\n{\"action_type\": \"click\", \"target\": (685,803)}"
}
] |
What's the time in New York?
|
click
|
{
"answer": null,
"center": [
0.685,
0.803
],
"direction": null,
"goal_status": null,
"original_action_type": "tap",
"text": null
}
|
[
"Hit a task-related element"
] |
Press on a task-related element
|
Press on a task-related element
|
GUICourse/GUIAct/imgs/uid_episode_31257933348203510_step_01.png
|
{
"action_type": "click",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": null,
"start": null,
"step_idx": 1,
"target": [
685,
803
],
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_31257933348203510-02
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: What's the time in New York?\nAction history: Step 1. Hit a task-related element. Step 2. Press on a task-related element.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Touch a task-related element<|object_ref_end|>\n{\"action_type\": \"click\", \"target\": (450,59)}"
}
] |
What's the time in New York?
|
click
|
{
"answer": null,
"center": [
0.45,
0.059000000000000004
],
"direction": null,
"goal_status": null,
"original_action_type": "tap",
"text": null
}
|
[
"Hit a task-related element",
"Press on a task-related element"
] |
Touch a task-related element
|
Touch a task-related element
|
GUICourse/GUIAct/imgs/uid_episode_31257933348203510_step_02.png
|
{
"action_type": "click",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": null,
"start": null,
"step_idx": 2,
"target": [
450,
59
],
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_31257933348203510-03
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: What's the time in New York?\nAction history: Step 1. Hit a task-related element. Step 2. Press on a task-related element. Step 3. Touch a task-related element.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Type \"What's the time in New York?\" into the text box<|object_ref_end|>\n{\"action_type\": \"input_text\", \"text\": \"What's the time in New York?\"}"
}
] |
What's the time in New York?
|
input_text
|
{
"answer": null,
"center": null,
"direction": null,
"goal_status": null,
"original_action_type": "input",
"text": "What's the time in New York?"
}
|
[
"Hit a task-related element",
"Press on a task-related element",
"Touch a task-related element"
] |
Type "What's the time in New York?" into the text box
|
Type "What's the time in New York?" into the text box
|
GUICourse/GUIAct/imgs/uid_episode_31257933348203510_step_03.png
|
{
"action_type": "input_text",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": null,
"start": null,
"step_idx": 3,
"target": null,
"text": "What's the time in New York?"
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_31257933348203510-04
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: What's the time in New York?\nAction history: Step 1. Hit a task-related element. Step 2. Press on a task-related element. Step 3. Touch a task-related element. Step 4. Type \"What's the time in New York?\" into the text box.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Tap the Enter key to confirm the input<|object_ref_end|>\n{\"action_type\": \"press_key\", \"key\": \"Enter\"}"
}
] |
What's the time in New York?
|
press_key
|
{
"answer": null,
"center": null,
"direction": null,
"goal_status": null,
"original_action_type": "enter",
"text": null
}
|
[
"Hit a task-related element",
"Press on a task-related element",
"Touch a task-related element",
"Type \"What's the time in New York?\" into the text box"
] |
Tap the Enter key to confirm the input.
|
Tap the Enter key to confirm the input
|
GUICourse/GUIAct/imgs/uid_episode_31257933348203510_step_04.png
|
{
"action_type": "press_key",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": "Enter",
"start": null,
"step_idx": 4,
"target": null,
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_31257933348203510-05
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: What's the time in New York?\nAction history: Step 1. Hit a task-related element. Step 2. Press on a task-related element. Step 3. Touch a task-related element. Step 4. Type \"What's the time in New York?\" into the text box. Step 5. Tap the Enter key to confirm the input.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Successfully completed the task<|object_ref_end|>\n{\"action_type\": \"status\", \"goal_status\": \"successful\", \"answer\": \"\"}"
}
] |
What's the time in New York?
|
status
|
{
"answer": "",
"center": null,
"direction": null,
"goal_status": "successful",
"original_action_type": "answer",
"text": null
}
|
[
"Hit a task-related element",
"Press on a task-related element",
"Touch a task-related element",
"Type \"What's the time in New York?\" into the text box",
"Tap the Enter key to confirm the input."
] |
Successfully completed the task.
|
Successfully completed the task
|
GUICourse/GUIAct/imgs/uid_episode_31257933348203510_step_05.png
|
{
"action_type": "status",
"answer": "",
"direction": null,
"distance": null,
"goal_status": "successful",
"key": null,
"start": null,
"step_idx": 5,
"target": null,
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_2311732173732608504-00
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: Where can I buy a nice beach chair?\nAction history: None\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Hit a task-related element<|object_ref_end|>\n{\"action_type\": \"click\", \"target\": (694,809)}"
}
] |
Where can I buy a nice beach chair?
|
click
|
{
"answer": null,
"center": [
0.6940000000000001,
0.809
],
"direction": null,
"goal_status": null,
"original_action_type": "tap",
"text": null
}
|
[] |
Hit a task-related element
|
Hit a task-related element
|
GUICourse/GUIAct/imgs/uid_episode_2311732173732608504_step_00.png
|
{
"action_type": "click",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": null,
"start": null,
"step_idx": 0,
"target": [
694,
809
],
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_2311732173732608504-01
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: Where can I buy a nice beach chair?\nAction history: Step 1. Hit a task-related element.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Press on a task-related element<|object_ref_end|>\n{\"action_type\": \"click\", \"target\": (747,194)}"
}
] |
Where can I buy a nice beach chair?
|
click
|
{
"answer": null,
"center": [
0.747,
0.194
],
"direction": null,
"goal_status": null,
"original_action_type": "tap",
"text": null
}
|
[
"Hit a task-related element"
] |
Press on a task-related element
|
Press on a task-related element
|
GUICourse/GUIAct/imgs/uid_episode_2311732173732608504_step_01.png
|
{
"action_type": "click",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": null,
"start": null,
"step_idx": 1,
"target": [
747,
194
],
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_2311732173732608504-02
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: Where can I buy a nice beach chair?\nAction history: Step 1. Hit a task-related element. Step 2. Press on a task-related element.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Touch a task-related element<|object_ref_end|>\n{\"action_type\": \"click\", \"target\": (933,127)}"
}
] |
Where can I buy a nice beach chair?
|
click
|
{
"answer": null,
"center": [
0.933,
0.127
],
"direction": null,
"goal_status": null,
"original_action_type": "tap",
"text": null
}
|
[
"Hit a task-related element",
"Press on a task-related element"
] |
Touch a task-related element
|
Touch a task-related element
|
GUICourse/GUIAct/imgs/uid_episode_2311732173732608504_step_02.png
|
{
"action_type": "click",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": null,
"start": null,
"step_idx": 2,
"target": [
933,
127
],
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_2311732173732608504-03
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: Where can I buy a nice beach chair?\nAction history: Step 1. Hit a task-related element. Step 2. Press on a task-related element. Step 3. Touch a task-related element.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Input text \"Where can I buy a nice beach chair?\" into the text box<|object_ref_end|>\n{\"action_type\": \"input_text\", \"text\": \"Where can I buy a nice beach chair?\"}"
}
] |
Where can I buy a nice beach chair?
|
input_text
|
{
"answer": null,
"center": null,
"direction": null,
"goal_status": null,
"original_action_type": "input",
"text": "Where can I buy a nice beach chair?"
}
|
[
"Hit a task-related element",
"Press on a task-related element",
"Touch a task-related element"
] |
Input text "Where can I buy a nice beach chair?" into the text box
|
Input text "Where can I buy a nice beach chair?" into the text box
|
GUICourse/GUIAct/imgs/uid_episode_2311732173732608504_step_03.png
|
{
"action_type": "input_text",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": null,
"start": null,
"step_idx": 3,
"target": null,
"text": "Where can I buy a nice beach chair?"
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_2311732173732608504-04
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: Where can I buy a nice beach chair?\nAction history: Step 1. Hit a task-related element. Step 2. Press on a task-related element. Step 3. Touch a task-related element. Step 4. Input text \"Where can I buy a nice beach chair?\" into the text box.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Tap the Enter key to submit<|object_ref_end|>\n{\"action_type\": \"press_key\", \"key\": \"Enter\"}"
}
] |
Where can I buy a nice beach chair?
|
press_key
|
{
"answer": null,
"center": null,
"direction": null,
"goal_status": null,
"original_action_type": "enter",
"text": null
}
|
[
"Hit a task-related element",
"Press on a task-related element",
"Touch a task-related element",
"Input text \"Where can I buy a nice beach chair?\" into the text box"
] |
Tap the Enter key to submit.
|
Tap the Enter key to submit
|
GUICourse/GUIAct/imgs/uid_episode_2311732173732608504_step_04.png
|
{
"action_type": "press_key",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": "Enter",
"start": null,
"step_idx": 4,
"target": null,
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_2311732173732608504-05
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: Where can I buy a nice beach chair?\nAction history: Step 1. Hit a task-related element. Step 2. Press on a task-related element. Step 3. Touch a task-related element. Step 4. Input text \"Where can I buy a nice beach chair?\" into the text box. Step 5. Tap the Enter key to submit.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>We have successfully finished the task<|object_ref_end|>\n{\"action_type\": \"status\", \"goal_status\": \"successful\", \"answer\": \"\"}"
}
] |
Where can I buy a nice beach chair?
|
status
|
{
"answer": "",
"center": null,
"direction": null,
"goal_status": "successful",
"original_action_type": "answer",
"text": null
}
|
[
"Hit a task-related element",
"Press on a task-related element",
"Touch a task-related element",
"Input text \"Where can I buy a nice beach chair?\" into the text box",
"Tap the Enter key to submit."
] |
We have successfully finished the task.
|
We have successfully finished the task
|
GUICourse/GUIAct/imgs/uid_episode_2311732173732608504_step_05.png
|
{
"action_type": "status",
"answer": "",
"direction": null,
"distance": null,
"goal_status": "successful",
"key": null,
"start": null,
"step_idx": 5,
"target": null,
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_7612430430445183382-00
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: What's on the menu at Starbucks?\nAction history: None\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Touch a task-related element<|object_ref_end|>\n{\"action_type\": \"click\", \"target\": (700,789)}"
}
] |
What's on the menu at Starbucks?
|
click
|
{
"answer": null,
"center": [
0.7000000000000001,
0.789
],
"direction": null,
"goal_status": null,
"original_action_type": "tap",
"text": null
}
|
[] |
Touch a task-related element
|
Touch a task-related element
|
GUICourse/GUIAct/imgs/uid_episode_7612430430445183382_step_00.png
|
{
"action_type": "click",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": null,
"start": null,
"step_idx": 0,
"target": [
700,
789
],
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_7612430430445183382-01
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: What's on the menu at Starbucks?\nAction history: Step 1. Touch a task-related element.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Hit a task-related element<|object_ref_end|>\n{\"action_type\": \"click\", \"target\": (700,789)}"
}
] |
What's on the menu at Starbucks?
|
click
|
{
"answer": null,
"center": [
0.7000000000000001,
0.789
],
"direction": null,
"goal_status": null,
"original_action_type": "tap",
"text": null
}
|
[
"Touch a task-related element"
] |
Hit a task-related element
|
Hit a task-related element
|
GUICourse/GUIAct/imgs/uid_episode_7612430430445183382_step_01.png
|
{
"action_type": "click",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": null,
"start": null,
"step_idx": 1,
"target": [
700,
789
],
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_7612430430445183382-02
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: What's on the menu at Starbucks?\nAction history: Step 1. Touch a task-related element. Step 2. Hit a task-related element.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Tap on a task-related element<|object_ref_end|>\n{\"action_type\": \"click\", \"target\": (414,47)}"
}
] |
What's on the menu at Starbucks?
|
click
|
{
"answer": null,
"center": [
0.41400000000000003,
0.047
],
"direction": null,
"goal_status": null,
"original_action_type": "tap",
"text": null
}
|
[
"Touch a task-related element",
"Hit a task-related element"
] |
Tap on a task-related element
|
Tap on a task-related element
|
GUICourse/GUIAct/imgs/uid_episode_7612430430445183382_step_02.png
|
{
"action_type": "click",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": null,
"start": null,
"step_idx": 2,
"target": [
414,
47
],
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_7612430430445183382-03
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: What's on the menu at Starbucks?\nAction history: Step 1. Touch a task-related element. Step 2. Hit a task-related element. Step 3. Tap on a task-related element.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Input text \"menu at starbucks\" into the text box<|object_ref_end|>\n{\"action_type\": \"input_text\", \"text\": \"menu at starbucks\"}"
}
] |
What's on the menu at Starbucks?
|
input_text
|
{
"answer": null,
"center": null,
"direction": null,
"goal_status": null,
"original_action_type": "input",
"text": "menu at starbucks"
}
|
[
"Touch a task-related element",
"Hit a task-related element",
"Tap on a task-related element"
] |
Input text "menu at starbucks" into the text box
|
Input text "menu at starbucks" into the text box
|
GUICourse/GUIAct/imgs/uid_episode_7612430430445183382_step_03.png
|
{
"action_type": "input_text",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": null,
"start": null,
"step_idx": 3,
"target": null,
"text": "menu at starbucks"
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_7612430430445183382-04
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: What's on the menu at Starbucks?\nAction history: Step 1. Touch a task-related element. Step 2. Hit a task-related element. Step 3. Tap on a task-related element. Step 4. Input text \"menu at starbucks\" into the text box.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Tap the Enter key to confirm<|object_ref_end|>\n{\"action_type\": \"press_key\", \"key\": \"Enter\"}"
}
] |
What's on the menu at Starbucks?
|
press_key
|
{
"answer": null,
"center": null,
"direction": null,
"goal_status": null,
"original_action_type": "enter",
"text": null
}
|
[
"Touch a task-related element",
"Hit a task-related element",
"Tap on a task-related element",
"Input text \"menu at starbucks\" into the text box"
] |
Tap the Enter key to confirm.
|
Tap the Enter key to confirm
|
GUICourse/GUIAct/imgs/uid_episode_7612430430445183382_step_04.png
|
{
"action_type": "press_key",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": "Enter",
"start": null,
"step_idx": 4,
"target": null,
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_7612430430445183382-05
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: What's on the menu at Starbucks?\nAction history: Step 1. Touch a task-related element. Step 2. Hit a task-related element. Step 3. Tap on a task-related element. Step 4. Input text \"menu at starbucks\" into the text box. Step 5. Tap the Enter key to confirm.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Touch a task-related element<|object_ref_end|>\n{\"action_type\": \"click\", \"target\": (346,376)}"
}
] |
What's on the menu at Starbucks?
|
click
|
{
"answer": null,
"center": [
0.34600000000000003,
0.376
],
"direction": null,
"goal_status": null,
"original_action_type": "tap",
"text": null
}
|
[
"Touch a task-related element",
"Hit a task-related element",
"Tap on a task-related element",
"Input text \"menu at starbucks\" into the text box",
"Tap the Enter key to confirm."
] |
Touch a task-related element
|
Touch a task-related element
|
GUICourse/GUIAct/imgs/uid_episode_7612430430445183382_step_05.png
|
{
"action_type": "click",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": null,
"start": null,
"step_idx": 5,
"target": [
346,
376
],
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_7612430430445183382-06
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: What's on the menu at Starbucks?\nAction history: Step 1. Touch a task-related element. Step 2. Hit a task-related element. Step 3. Tap on a task-related element. Step 4. Input text \"menu at starbucks\" into the text box. Step 5. Tap the Enter key to confirm. Step 6. Touch a task-related element.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Touch a task-related element<|object_ref_end|>\n{\"action_type\": \"click\", \"target\": (214,981)}"
}
] |
What's on the menu at Starbucks?
|
click
|
{
"answer": null,
"center": [
0.214,
0.981
],
"direction": null,
"goal_status": null,
"original_action_type": "tap",
"text": null
}
|
[
"Touch a task-related element",
"Hit a task-related element",
"Tap on a task-related element",
"Input text \"menu at starbucks\" into the text box",
"Tap the Enter key to confirm.",
"Touch a task-related element"
] |
Touch a task-related element
|
Touch a task-related element
|
GUICourse/GUIAct/imgs/uid_episode_7612430430445183382_step_06.png
|
{
"action_type": "click",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": null,
"start": null,
"step_idx": 6,
"target": [
214,
981
],
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_7612430430445183382-07
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: What's on the menu at Starbucks?\nAction history: Step 1. Touch a task-related element. Step 2. Hit a task-related element. Step 3. Tap on a task-related element. Step 4. Input text \"menu at starbucks\" into the text box. Step 5. Tap the Enter key to confirm. Step 6. Touch a task-related element.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Press on a task-related element<|object_ref_end|>\n{\"action_type\": \"click\", \"target\": (415,390)}"
}
] |
What's on the menu at Starbucks?
|
click
|
{
"answer": null,
"center": [
0.41500000000000004,
0.39
],
"direction": null,
"goal_status": null,
"original_action_type": "tap",
"text": null
}
|
[
"Touch a task-related element",
"Hit a task-related element",
"Tap on a task-related element",
"Input text \"menu at starbucks\" into the text box",
"Tap the Enter key to confirm.",
"Touch a task-related element",
"Touch a task-related element"
] |
Press on a task-related element
|
Press on a task-related element
|
GUICourse/GUIAct/imgs/uid_episode_7612430430445183382_step_07.png
|
{
"action_type": "click",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": null,
"start": null,
"step_idx": 7,
"target": [
415,
390
],
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_7612430430445183382-08
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: What's on the menu at Starbucks?\nAction history: Step 2. Hit a task-related element. Step 3. Tap on a task-related element. Step 4. Input text \"menu at starbucks\" into the text box. Step 5. Tap the Enter key to confirm. Step 6. Touch a task-related element. Step 7. Press on a task-related element.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Hit a task-related element<|object_ref_end|>\n{\"action_type\": \"click\", \"target\": (811,560)}"
}
] |
What's on the menu at Starbucks?
|
click
|
{
"answer": null,
"center": [
0.811,
0.56
],
"direction": null,
"goal_status": null,
"original_action_type": "tap",
"text": null
}
|
[
"Touch a task-related element",
"Hit a task-related element",
"Tap on a task-related element",
"Input text \"menu at starbucks\" into the text box",
"Tap the Enter key to confirm.",
"Touch a task-related element",
"Touch a task-related element",
"Press on a task-related element"
] |
Hit a task-related element
|
Hit a task-related element
|
GUICourse/GUIAct/imgs/uid_episode_7612430430445183382_step_08.png
|
{
"action_type": "click",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": null,
"start": null,
"step_idx": 8,
"target": [
811,
560
],
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_7612430430445183382-09
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: What's on the menu at Starbucks?\nAction history: Step 3. Tap on a task-related element. Step 4. Input text \"menu at starbucks\" into the text box. Step 5. Tap the Enter key to confirm. Step 6. Touch a task-related element. Step 7. Press on a task-related element. Step 8. Hit a task-related element.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Touch a task-related element<|object_ref_end|>\n{\"action_type\": \"click\", \"target\": (575,443)}"
}
] |
What's on the menu at Starbucks?
|
click
|
{
"answer": null,
"center": [
0.5750000000000001,
0.443
],
"direction": null,
"goal_status": null,
"original_action_type": "tap",
"text": null
}
|
[
"Touch a task-related element",
"Hit a task-related element",
"Tap on a task-related element",
"Input text \"menu at starbucks\" into the text box",
"Tap the Enter key to confirm.",
"Touch a task-related element",
"Touch a task-related element",
"Press on a task-related element",
"Hit a task-related element"
] |
Touch a task-related element
|
Touch a task-related element
|
GUICourse/GUIAct/imgs/uid_episode_7612430430445183382_step_09.png
|
{
"action_type": "click",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": null,
"start": null,
"step_idx": 9,
"target": [
575,
443
],
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_7612430430445183382-10
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: What's on the menu at Starbucks?\nAction history: Step 4. Input text \"menu at starbucks\" into the text box. Step 5. Tap the Enter key to confirm. Step 6. Touch a task-related element. Step 7. Press on a task-related element. Step 8. Hit a task-related element. Step 9. Touch a task-related element.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Successfully completed the task<|object_ref_end|>\n{\"action_type\": \"status\", \"goal_status\": \"successful\", \"answer\": \"\"}"
}
] |
What's on the menu at Starbucks?
|
status
|
{
"answer": "",
"center": null,
"direction": null,
"goal_status": "successful",
"original_action_type": "answer",
"text": null
}
|
[
"Touch a task-related element",
"Hit a task-related element",
"Tap on a task-related element",
"Input text \"menu at starbucks\" into the text box",
"Tap the Enter key to confirm.",
"Touch a task-related element",
"Touch a task-related element",
"Press on a task-related element",
"Hit a task-related element",
"Touch a task-related element"
] |
Successfully completed the task.
|
Successfully completed the task
|
GUICourse/GUIAct/imgs/uid_episode_7612430430445183382_step_10.png
|
{
"action_type": "status",
"answer": "",
"direction": null,
"distance": null,
"goal_status": "successful",
"key": null,
"start": null,
"step_idx": 10,
"target": null,
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_17851593393449707315-00
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: How much does a 3 bedroom apartment rent for in Philadelphia?\nAction history: None\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Touch a task-related element<|object_ref_end|>\n{\"action_type\": \"click\", \"target\": (503,981)}"
}
] |
How much does a 3 bedroom apartment rent for in Philadelphia?
|
click
|
{
"answer": null,
"center": [
0.503,
0.981
],
"direction": null,
"goal_status": null,
"original_action_type": "tap",
"text": null
}
|
[] |
Touch a task-related element
|
Touch a task-related element
|
GUICourse/GUIAct/imgs/uid_episode_17851593393449707315_step_00.png
|
{
"action_type": "click",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": null,
"start": null,
"step_idx": 0,
"target": [
503,
981
],
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_17851593393449707315-01
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: How much does a 3 bedroom apartment rent for in Philadelphia?\nAction history: Step 1. Touch a task-related element.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Press on a task-related element<|object_ref_end|>\n{\"action_type\": \"click\", \"target\": (676,805)}"
}
] |
How much does a 3 bedroom apartment rent for in Philadelphia?
|
click
|
{
"answer": null,
"center": [
0.676,
0.805
],
"direction": null,
"goal_status": null,
"original_action_type": "tap",
"text": null
}
|
[
"Touch a task-related element"
] |
Press on a task-related element
|
Press on a task-related element
|
GUICourse/GUIAct/imgs/uid_episode_17851593393449707315_step_01.png
|
{
"action_type": "click",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": null,
"start": null,
"step_idx": 1,
"target": [
676,
805
],
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_17851593393449707315-02
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: How much does a 3 bedroom apartment rent for in Philadelphia?\nAction history: Step 1. Touch a task-related element. Step 2. Press on a task-related element.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Tap on a task-related element<|object_ref_end|>\n{\"action_type\": \"click\", \"target\": (578,60)}"
}
] |
How much does a 3 bedroom apartment rent for in Philadelphia?
|
click
|
{
"answer": null,
"center": [
0.578,
0.06
],
"direction": null,
"goal_status": null,
"original_action_type": "tap",
"text": null
}
|
[
"Touch a task-related element",
"Press on a task-related element"
] |
Tap on a task-related element
|
Tap on a task-related element
|
GUICourse/GUIAct/imgs/uid_episode_17851593393449707315_step_02.png
|
{
"action_type": "click",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": null,
"start": null,
"step_idx": 2,
"target": [
578,
60
],
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_17851593393449707315-03
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: How much does a 3 bedroom apartment rent for in Philadelphia?\nAction history: Step 1. Touch a task-related element. Step 2. Press on a task-related element. Step 3. Tap on a task-related element.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Fill \"How much does a 3 bedroom apartment rent for in Philadelphia?\" in the text box<|object_ref_end|>\n{\"action_type\": \"input_text\", \"text\": \"How much does a 3 bedroom apartment rent for in Philadelphia?\"}"
}
] |
How much does a 3 bedroom apartment rent for in Philadelphia?
|
input_text
|
{
"answer": null,
"center": null,
"direction": null,
"goal_status": null,
"original_action_type": "input",
"text": "How much does a 3 bedroom apartment rent for in Philadelphia?"
}
|
[
"Touch a task-related element",
"Press on a task-related element",
"Tap on a task-related element"
] |
Fill "How much does a 3 bedroom apartment rent for in Philadelphia?" in the text box
|
Fill "How much does a 3 bedroom apartment rent for in Philadelphia?" in the text box
|
GUICourse/GUIAct/imgs/uid_episode_17851593393449707315_step_03.png
|
{
"action_type": "input_text",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": null,
"start": null,
"step_idx": 3,
"target": null,
"text": "How much does a 3 bedroom apartment rent for in Philadelphia?"
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_17851593393449707315-04
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: How much does a 3 bedroom apartment rent for in Philadelphia?\nAction history: Step 1. Touch a task-related element. Step 2. Press on a task-related element. Step 3. Tap on a task-related element. Step 4. Fill \"How much does a 3 bedroom apartment rent for in Philadelphia?\" in the text box.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Tap the Enter key to submit<|object_ref_end|>\n{\"action_type\": \"press_key\", \"key\": \"Enter\"}"
}
] |
How much does a 3 bedroom apartment rent for in Philadelphia?
|
press_key
|
{
"answer": null,
"center": null,
"direction": null,
"goal_status": null,
"original_action_type": "enter",
"text": null
}
|
[
"Touch a task-related element",
"Press on a task-related element",
"Tap on a task-related element",
"Fill \"How much does a 3 bedroom apartment rent for in Philadelphia?\" in the text box"
] |
Tap the Enter key to submit.
|
Tap the Enter key to submit
|
GUICourse/GUIAct/imgs/uid_episode_17851593393449707315_step_04.png
|
{
"action_type": "press_key",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": "Enter",
"start": null,
"step_idx": 4,
"target": null,
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_17851593393449707315-05
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: How much does a 3 bedroom apartment rent for in Philadelphia?\nAction history: Step 1. Touch a task-related element. Step 2. Press on a task-related element. Step 3. Tap on a task-related element. Step 4. Fill \"How much does a 3 bedroom apartment rent for in Philadelphia?\" in the text box. Step 5. Tap the Enter key to submit.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Swipe up to reveal the target<|object_ref_end|>\n{\"action_type\": \"swipe\", \"start\": (653,815), \"direction\": \"up\", \"distance\": \"long\"}"
}
] |
How much does a 3 bedroom apartment rent for in Philadelphia?
|
swipe
|
{
"answer": null,
"center": null,
"direction": "up",
"goal_status": null,
"original_action_type": "swipe",
"text": null
}
|
[
"Touch a task-related element",
"Press on a task-related element",
"Tap on a task-related element",
"Fill \"How much does a 3 bedroom apartment rent for in Philadelphia?\" in the text box",
"Tap the Enter key to submit."
] |
Swipe up to reveal the target
|
Swipe up to reveal the target
|
GUICourse/GUIAct/imgs/uid_episode_17851593393449707315_step_05.png
|
{
"action_type": "swipe",
"answer": null,
"direction": "up",
"distance": "long",
"goal_status": null,
"key": null,
"start": [
653,
815
],
"step_idx": 5,
"target": null,
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_17851593393449707315-06
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: How much does a 3 bedroom apartment rent for in Philadelphia?\nAction history: Step 1. Touch a task-related element. Step 2. Press on a task-related element. Step 3. Tap on a task-related element. Step 4. Fill \"How much does a 3 bedroom apartment rent for in Philadelphia?\" in the text box. Step 5. Tap the Enter key to submit. Step 6. Swipe up to reveal the target.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Click on a task-related element<|object_ref_end|>\n{\"action_type\": \"click\", \"target\": (497,550)}"
}
] |
How much does a 3 bedroom apartment rent for in Philadelphia?
|
click
|
{
"answer": null,
"center": [
0.497,
0.55
],
"direction": null,
"goal_status": null,
"original_action_type": "tap",
"text": null
}
|
[
"Touch a task-related element",
"Press on a task-related element",
"Tap on a task-related element",
"Fill \"How much does a 3 bedroom apartment rent for in Philadelphia?\" in the text box",
"Tap the Enter key to submit.",
"Swipe up to reveal the target"
] |
Click on a task-related element
|
Click on a task-related element
|
GUICourse/GUIAct/imgs/uid_episode_17851593393449707315_step_06.png
|
{
"action_type": "click",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": null,
"start": null,
"step_idx": 6,
"target": [
497,
550
],
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_17851593393449707315-07
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: How much does a 3 bedroom apartment rent for in Philadelphia?\nAction history: Step 2. Press on a task-related element. Step 3. Tap on a task-related element. Step 4. Fill \"How much does a 3 bedroom apartment rent for in Philadelphia?\" in the text box. Step 5. Tap the Enter key to submit. Step 6. Swipe up to reveal the target. Step 7. Click on a task-related element.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>We have successfully finished the task<|object_ref_end|>\n{\"action_type\": \"status\", \"goal_status\": \"successful\", \"answer\": \"\"}"
}
] |
How much does a 3 bedroom apartment rent for in Philadelphia?
|
status
|
{
"answer": "",
"center": null,
"direction": null,
"goal_status": "successful",
"original_action_type": "answer",
"text": null
}
|
[
"Touch a task-related element",
"Press on a task-related element",
"Tap on a task-related element",
"Fill \"How much does a 3 bedroom apartment rent for in Philadelphia?\" in the text box",
"Tap the Enter key to submit.",
"Swipe up to reveal the target",
"Click on a task-related element"
] |
We have successfully finished the task.
|
We have successfully finished the task
|
GUICourse/GUIAct/imgs/uid_episode_17851593393449707315_step_07.png
|
{
"action_type": "status",
"answer": "",
"direction": null,
"distance": null,
"goal_status": "successful",
"key": null,
"start": null,
"step_idx": 7,
"target": null,
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_14964119257570835434-00
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: What's the news about the US dollar exchange rate?\nAction history: None\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Enter text \"What's the news about the US dollar exchange rate?\" in the text box<|object_ref_end|>\n{\"action_type\": \"input_text\", \"text\": \"What's the news about the US dollar exchange rate?\"}"
}
] |
What's the news about the US dollar exchange rate?
|
input_text
|
{
"answer": null,
"center": null,
"direction": null,
"goal_status": null,
"original_action_type": "input",
"text": "What's the news about the US dollar exchange rate?"
}
|
[] |
Enter text "What's the news about the US dollar exchange rate?" in the text box
|
Enter text "What's the news about the US dollar exchange rate?" in the text box
|
GUICourse/GUIAct/imgs/uid_episode_14964119257570835434_step_00.png
|
{
"action_type": "input_text",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": null,
"start": null,
"step_idx": 0,
"target": null,
"text": "What's the news about the US dollar exchange rate?"
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_14964119257570835434-01
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: What's the news about the US dollar exchange rate?\nAction history: Step 1. Enter text \"What's the news about the US dollar exchange rate?\" in the text box.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Press the Enter key to confirm the input<|object_ref_end|>\n{\"action_type\": \"press_key\", \"key\": \"Enter\"}"
}
] |
What's the news about the US dollar exchange rate?
|
press_key
|
{
"answer": null,
"center": null,
"direction": null,
"goal_status": null,
"original_action_type": "enter",
"text": null
}
|
[
"Enter text \"What's the news about the US dollar exchange rate?\" in the text box"
] |
Press the Enter key to confirm the input.
|
Press the Enter key to confirm the input
|
GUICourse/GUIAct/imgs/uid_episode_14964119257570835434_step_01.png
|
{
"action_type": "press_key",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": "Enter",
"start": null,
"step_idx": 1,
"target": null,
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_14964119257570835434-02
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: What's the news about the US dollar exchange rate?\nAction history: Step 1. Enter text \"What's the news about the US dollar exchange rate?\" in the text box. Step 2. Press the Enter key to confirm the input.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Hit a task-related element<|object_ref_end|>\n{\"action_type\": \"click\", \"target\": (197,170)}"
}
] |
What's the news about the US dollar exchange rate?
|
click
|
{
"answer": null,
"center": [
0.197,
0.17
],
"direction": null,
"goal_status": null,
"original_action_type": "tap",
"text": null
}
|
[
"Enter text \"What's the news about the US dollar exchange rate?\" in the text box",
"Press the Enter key to confirm the input."
] |
Hit a task-related element
|
Hit a task-related element
|
GUICourse/GUIAct/imgs/uid_episode_14964119257570835434_step_02.png
|
{
"action_type": "click",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": null,
"start": null,
"step_idx": 2,
"target": [
197,
170
],
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_14964119257570835434-03
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: What's the news about the US dollar exchange rate?\nAction history: Step 1. Enter text \"What's the news about the US dollar exchange rate?\" in the text box. Step 2. Press the Enter key to confirm the input. Step 3. Hit a task-related element.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Press on a task-related element<|object_ref_end|>\n{\"action_type\": \"click\", \"target\": (664,252)}"
}
] |
What's the news about the US dollar exchange rate?
|
click
|
{
"answer": null,
"center": [
0.664,
0.252
],
"direction": null,
"goal_status": null,
"original_action_type": "tap",
"text": null
}
|
[
"Enter text \"What's the news about the US dollar exchange rate?\" in the text box",
"Press the Enter key to confirm the input.",
"Hit a task-related element"
] |
Press on a task-related element
|
Press on a task-related element
|
GUICourse/GUIAct/imgs/uid_episode_14964119257570835434_step_03.png
|
{
"action_type": "click",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": null,
"start": null,
"step_idx": 3,
"target": [
664,
252
],
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_14964119257570835434-04
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: What's the news about the US dollar exchange rate?\nAction history: Step 1. Enter text \"What's the news about the US dollar exchange rate?\" in the text box. Step 2. Press the Enter key to confirm the input. Step 3. Hit a task-related element. Step 4. Press on a task-related element.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Successfully completed the task<|object_ref_end|>\n{\"action_type\": \"status\", \"goal_status\": \"successful\", \"answer\": \"\"}"
}
] |
What's the news about the US dollar exchange rate?
|
status
|
{
"answer": "",
"center": null,
"direction": null,
"goal_status": "successful",
"original_action_type": "answer",
"text": null
}
|
[
"Enter text \"What's the news about the US dollar exchange rate?\" in the text box",
"Press the Enter key to confirm the input.",
"Hit a task-related element",
"Press on a task-related element"
] |
Successfully completed the task.
|
Successfully completed the task
|
GUICourse/GUIAct/imgs/uid_episode_14964119257570835434_step_04.png
|
{
"action_type": "status",
"answer": "",
"direction": null,
"distance": null,
"goal_status": "successful",
"key": null,
"start": null,
"step_idx": 4,
"target": null,
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_14123550702844468128-00
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: Search for flights from NYC to Tokyo\nAction history: None\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Press on a task-related element<|object_ref_end|>\n{\"action_type\": \"click\", \"target\": (714,791)}"
}
] |
Search for flights from NYC to Tokyo
|
click
|
{
"answer": null,
"center": [
0.714,
0.791
],
"direction": null,
"goal_status": null,
"original_action_type": "tap",
"text": null
}
|
[] |
Press on a task-related element
|
Press on a task-related element
|
GUICourse/GUIAct/imgs/uid_episode_14123550702844468128_step_00.png
|
{
"action_type": "click",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": null,
"start": null,
"step_idx": 0,
"target": [
714,
791
],
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_14123550702844468128-01
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: Search for flights from NYC to Tokyo\nAction history: Step 1. Press on a task-related element.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Touch a task-related element<|object_ref_end|>\n{\"action_type\": \"click\", \"target\": (714,791)}"
}
] |
Search for flights from NYC to Tokyo
|
click
|
{
"answer": null,
"center": [
0.714,
0.791
],
"direction": null,
"goal_status": null,
"original_action_type": "tap",
"text": null
}
|
[
"Press on a task-related element"
] |
Touch a task-related element
|
Touch a task-related element
|
GUICourse/GUIAct/imgs/uid_episode_14123550702844468128_step_01.png
|
{
"action_type": "click",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": null,
"start": null,
"step_idx": 1,
"target": [
714,
791
],
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_14123550702844468128-02
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: Search for flights from NYC to Tokyo\nAction history: Step 1. Press on a task-related element. Step 2. Touch a task-related element.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Tap on a task-related element<|object_ref_end|>\n{\"action_type\": \"click\", \"target\": (714,791)}"
}
] |
Search for flights from NYC to Tokyo
|
click
|
{
"answer": null,
"center": [
0.714,
0.791
],
"direction": null,
"goal_status": null,
"original_action_type": "tap",
"text": null
}
|
[
"Press on a task-related element",
"Touch a task-related element"
] |
Tap on a task-related element
|
Tap on a task-related element
|
GUICourse/GUIAct/imgs/uid_episode_14123550702844468128_step_02.png
|
{
"action_type": "click",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": null,
"start": null,
"step_idx": 2,
"target": [
714,
791
],
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_14123550702844468128-03
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: Search for flights from NYC to Tokyo\nAction history: Step 1. Press on a task-related element. Step 2. Touch a task-related element. Step 3. Tap on a task-related element.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Press on a task-related element<|object_ref_end|>\n{\"action_type\": \"click\", \"target\": (562,61)}"
}
] |
Search for flights from NYC to Tokyo
|
click
|
{
"answer": null,
"center": [
0.562,
0.061
],
"direction": null,
"goal_status": null,
"original_action_type": "tap",
"text": null
}
|
[
"Press on a task-related element",
"Touch a task-related element",
"Tap on a task-related element"
] |
Press on a task-related element
|
Press on a task-related element
|
GUICourse/GUIAct/imgs/uid_episode_14123550702844468128_step_03.png
|
{
"action_type": "click",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": null,
"start": null,
"step_idx": 3,
"target": [
562,
61
],
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_14123550702844468128-04
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: Search for flights from NYC to Tokyo\nAction history: Step 1. Press on a task-related element. Step 2. Touch a task-related element. Step 3. Tap on a task-related element. Step 4. Press on a task-related element.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Input text \"flights from NYC to Tokyo\" into the text box<|object_ref_end|>\n{\"action_type\": \"input_text\", \"text\": \"flights from NYC to Tokyo\"}"
}
] |
Search for flights from NYC to Tokyo
|
input_text
|
{
"answer": null,
"center": null,
"direction": null,
"goal_status": null,
"original_action_type": "input",
"text": "flights from NYC to Tokyo"
}
|
[
"Press on a task-related element",
"Touch a task-related element",
"Tap on a task-related element",
"Press on a task-related element"
] |
Input text "flights from NYC to Tokyo" into the text box
|
Input text "flights from NYC to Tokyo" into the text box
|
GUICourse/GUIAct/imgs/uid_episode_14123550702844468128_step_04.png
|
{
"action_type": "input_text",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": null,
"start": null,
"step_idx": 4,
"target": null,
"text": "flights from NYC to Tokyo"
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_14123550702844468128-05
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: Search for flights from NYC to Tokyo\nAction history: Step 1. Press on a task-related element. Step 2. Touch a task-related element. Step 3. Tap on a task-related element. Step 4. Press on a task-related element. Step 5. Input text \"flights from NYC to Tokyo\" into the text box.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Tap the Enter key to confirm the input<|object_ref_end|>\n{\"action_type\": \"press_key\", \"key\": \"Enter\"}"
}
] |
Search for flights from NYC to Tokyo
|
press_key
|
{
"answer": null,
"center": null,
"direction": null,
"goal_status": null,
"original_action_type": "enter",
"text": null
}
|
[
"Press on a task-related element",
"Touch a task-related element",
"Tap on a task-related element",
"Press on a task-related element",
"Input text \"flights from NYC to Tokyo\" into the text box"
] |
Tap the Enter key to confirm the input.
|
Tap the Enter key to confirm the input
|
GUICourse/GUIAct/imgs/uid_episode_14123550702844468128_step_05.png
|
{
"action_type": "press_key",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": "Enter",
"start": null,
"step_idx": 5,
"target": null,
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_14123550702844468128-06
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: Search for flights from NYC to Tokyo\nAction history: Step 1. Press on a task-related element. Step 2. Touch a task-related element. Step 3. Tap on a task-related element. Step 4. Press on a task-related element. Step 5. Input text \"flights from NYC to Tokyo\" into the text box. Step 6. Tap the Enter key to confirm the input.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>We have successfully finished the task<|object_ref_end|>\n{\"action_type\": \"status\", \"goal_status\": \"successful\", \"answer\": \"\"}"
}
] |
Search for flights from NYC to Tokyo
|
status
|
{
"answer": "",
"center": null,
"direction": null,
"goal_status": "successful",
"original_action_type": "answer",
"text": null
}
|
[
"Press on a task-related element",
"Touch a task-related element",
"Tap on a task-related element",
"Press on a task-related element",
"Input text \"flights from NYC to Tokyo\" into the text box",
"Tap the Enter key to confirm the input."
] |
We have successfully finished the task.
|
We have successfully finished the task
|
GUICourse/GUIAct/imgs/uid_episode_14123550702844468128_step_06.png
|
{
"action_type": "status",
"answer": "",
"direction": null,
"distance": null,
"goal_status": "successful",
"key": null,
"start": null,
"step_idx": 6,
"target": null,
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_6205788666296795236-00
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: How much does a 2 bedroom apartment rent for in Houston?\nAction history: None\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Tap on a task-related element<|object_ref_end|>\n{\"action_type\": \"click\", \"target\": (503,981)}"
}
] |
How much does a 2 bedroom apartment rent for in Houston?
|
click
|
{
"answer": null,
"center": [
0.503,
0.981
],
"direction": null,
"goal_status": null,
"original_action_type": "tap",
"text": null
}
|
[] |
Tap on a task-related element
|
Tap on a task-related element
|
GUICourse/GUIAct/imgs/uid_episode_6205788666296795236_step_00.png
|
{
"action_type": "click",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": null,
"start": null,
"step_idx": 0,
"target": [
503,
981
],
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_6205788666296795236-01
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: How much does a 2 bedroom apartment rent for in Houston?\nAction history: Step 1. Tap on a task-related element.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Hit a task-related element<|object_ref_end|>\n{\"action_type\": \"click\", \"target\": (686,787)}"
}
] |
How much does a 2 bedroom apartment rent for in Houston?
|
click
|
{
"answer": null,
"center": [
0.686,
0.787
],
"direction": null,
"goal_status": null,
"original_action_type": "tap",
"text": null
}
|
[
"Tap on a task-related element"
] |
Hit a task-related element
|
Hit a task-related element
|
GUICourse/GUIAct/imgs/uid_episode_6205788666296795236_step_01.png
|
{
"action_type": "click",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": null,
"start": null,
"step_idx": 1,
"target": [
686,
787
],
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_6205788666296795236-02
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: How much does a 2 bedroom apartment rent for in Houston?\nAction history: Step 1. Tap on a task-related element. Step 2. Hit a task-related element.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Hit a task-related element<|object_ref_end|>\n{\"action_type\": \"click\", \"target\": (686,795)}"
}
] |
How much does a 2 bedroom apartment rent for in Houston?
|
click
|
{
"answer": null,
"center": [
0.686,
0.795
],
"direction": null,
"goal_status": null,
"original_action_type": "tap",
"text": null
}
|
[
"Tap on a task-related element",
"Hit a task-related element"
] |
Hit a task-related element
|
Hit a task-related element
|
GUICourse/GUIAct/imgs/uid_episode_6205788666296795236_step_02.png
|
{
"action_type": "click",
"answer": null,
"direction": null,
"distance": null,
"goal_status": null,
"key": null,
"start": null,
"step_idx": 2,
"target": [
686,
795
],
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_6205788666296795236-03
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: How much does a 2 bedroom apartment rent for in Houston?\nAction history: Step 1. Tap on a task-related element. Step 2. Hit a task-related element.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Swipe down to discover additional content<|object_ref_end|>\n{\"action_type\": \"swipe\", \"start\": (457,372), \"direction\": \"down\", \"distance\": \"long\"}"
}
] |
How much does a 2 bedroom apartment rent for in Houston?
|
swipe
|
{
"answer": null,
"center": null,
"direction": "down",
"goal_status": null,
"original_action_type": "swipe",
"text": null
}
|
[
"Tap on a task-related element",
"Hit a task-related element",
"Hit a task-related element"
] |
Swipe down to discover additional content
|
Swipe down to discover additional content
|
GUICourse/GUIAct/imgs/uid_episode_6205788666296795236_step_03.png
|
{
"action_type": "swipe",
"answer": null,
"direction": "down",
"distance": "long",
"goal_status": null,
"key": null,
"start": [
457,
372
],
"step_idx": 3,
"target": null,
"text": null
}
|
720x1440
|
mobile
|
autogui_GUIAct-smartphone_planning_6205788666296795236-04
|
[
{
"from": "human",
"value": "<image>\nGiven the Android UI screenshot and previous actions, please generate the next move necessary to advance towards task completion. The user's task is: How much does a 2 bedroom apartment rent for in Houston?\nAction history: Step 1. Tap on a task-related element. Step 2. Hit a task-related element. Step 3. Swipe down to discover additional content.\n\nNow, first describe the action intent and then directly plan the next action."
},
{
"from": "gpt",
"value": "Action: <|object_ref_start|>Swipe down to reach the target page<|object_ref_end|>\n{\"action_type\": \"swipe\", \"start\": (450,297), \"direction\": \"down\", \"distance\": \"medium\"}"
}
] |
How much does a 2 bedroom apartment rent for in Houston?
|
swipe
|
{
"answer": null,
"center": null,
"direction": "down",
"goal_status": null,
"original_action_type": "swipe",
"text": null
}
|
[
"Tap on a task-related element",
"Hit a task-related element",
"Hit a task-related element",
"Swipe down to discover additional content"
] |
Swipe down to reach the target page
|
Swipe down to reach the target page
|
GUICourse/GUIAct/imgs/uid_episode_6205788666296795236_step_04.png
|
{
"action_type": "swipe",
"answer": null,
"direction": "down",
"distance": "medium",
"goal_status": null,
"key": null,
"start": [
450,
297
],
"step_idx": 4,
"target": null,
"text": null
}
|
720x1440
|
mobile
|
End of preview.
No dataset card yet
- Downloads last month
- 6