Dataset Viewer
Auto-converted to Parquet Duplicate
video_id
stringclasses
1 value
step
int32
0
105
system
stringclasses
1 value
user
stringlengths
188
5.36k
assistant
stringlengths
104
476
image
imagewidth (px)
1.3k
1.3k
video_001
0
You are an expert GUI agent. You will be given a task, the history of previous actions, and two screenshots ('Before' and 'After'). Your goal is to determine the single user action that occurred between the two screenshots to progress the task. CRITICAL: You MUST ONLY use these EXACT function names and signatures: <c...
Please generate the next move according to the UI screenshot, instruction and previous actions. Instruction: I want to hire a CEO for a Generative AI comapny in US Previous actions: None
<think> The user typed the text: 'I want to hire a CEO for a I want to hire a CEO for an AI company. Pl I want to hire a CEO for an AI company. Please give me some suitable candidates. Generative AI' </think> <code> type("I want to hire a CEO for a I want to hire a CEO for an AI company. Pl I want to hire a CEO for an ...
video_001
1
You are an expert GUI agent. You will be given a task, the history of previous actions, and two screenshots ('Before' and 'After'). Your goal is to determine the single user action that occurred between the two screenshots to progress the task. CRITICAL: You MUST ONLY use these EXACT function names and signatures: <c...
Please generate the next move according to the UI screenshot, instruction and previous actions. Instruction: I want to hire a CEO for a Generative AI comapny in US Previous actions: Step 1: type("I want to hire a CEO for a I want to hire a CEO for an AI company. Pl I want to hire a CEO for an AI company. Please give ...
<think> Ground truth action from DOM recording: click </think> <code> click(0.045, 0.025, "element") </code>
video_001
2
You are an expert GUI agent. You will be given a task, the history of previous actions, and two screenshots ('Before' and 'After'). Your goal is to determine the single user action that occurred between the two screenshots to progress the task. CRITICAL: You MUST ONLY use these EXACT function names and signatures: <c...
Please generate the next move according to the UI screenshot, instruction and previous actions. Instruction: I want to hire a CEO for a Generative AI comapny in US Previous actions: Step 1: type("I want to hire a CEO for a I want to hire a CEO for an AI company. Pl I want to hire a CEO for an AI company. Please give ...
<think> Ground truth action from DOM recording: click </think> <code> click(0.031, 0.016, "aria") </code>
video_001
3
You are an expert GUI agent. You will be given a task, the history of previous actions, and two screenshots ('Before' and 'After'). Your goal is to determine the single user action that occurred between the two screenshots to progress the task. CRITICAL: You MUST ONLY use these EXACT function names and signatures: <c...
Please generate the next move according to the UI screenshot, instruction and previous actions. Instruction: I want to hire a CEO for a Generative AI comapny in US Previous actions: Step 1: type("I want to hire a CEO for a I want to hire a CEO for an AI company. Pl I want to hire a CEO for an AI company. Please give ...
<think> Ground truth action from DOM recording: click </think> <code> click(0.082, 0.010, "styles bentoCardContainer ajBKM") </code>
video_001
4
You are an expert GUI agent. You will be given a task, the history of previous actions, and two screenshots ('Before' and 'After'). Your goal is to determine the single user action that occurred between the two screenshots to progress the task. CRITICAL: You MUST ONLY use these EXACT function names and signatures: <c...
Please generate the next move according to the UI screenshot, instruction and previous actions. Instruction: I want to hire a CEO for a Generative AI comapny in US Previous actions: Step 1: type("I want to hire a CEO for a I want to hire a CEO for an AI company. Pl I want to hire a CEO for an AI company. Please give ...
<think> Ground truth action from DOM recording: click </think> <code> click(0.030, 0.019, "aria") </code>
video_001
5
You are an expert GUI agent. You will be given a task, the history of previous actions, and two screenshots ('Before' and 'After'). Your goal is to determine the single user action that occurred between the two screenshots to progress the task. CRITICAL: You MUST ONLY use these EXACT function names and signatures: <c...
Please generate the next move according to the UI screenshot, instruction and previous actions. Instruction: I want to hire a CEO for a Generative AI comapny in US Previous actions: Step 1: type("I want to hire a CEO for a I want to hire a CEO for an AI company. Pl I want to hire a CEO for an AI company. Please give ...
<think> Ground truth action from DOM recording: click </think> <code> click(0.006, 0.007, "element") </code>
video_001
6
You are an expert GUI agent. You will be given a task, the history of previous actions, and two screenshots ('Before' and 'After'). Your goal is to determine the single user action that occurred between the two screenshots to progress the task. CRITICAL: You MUST ONLY use these EXACT function names and signatures: <c...
Please generate the next move according to the UI screenshot, instruction and previous actions. Instruction: I want to hire a CEO for a Generative AI comapny in US Previous actions: Step 1: type("I want to hire a CEO for a I want to hire a CEO for an AI company. Pl I want to hire a CEO for an AI company. Please give ...
<think> Ground truth action from DOM recording: click </think> <code> click(0.008, 0.006, "styles personViewHeaderContainer TJ6js") </code>
video_001
7
You are an expert GUI agent. You will be given a task, the history of previous actions, and two screenshots ('Before' and 'After'). Your goal is to determine the single user action that occurred between the two screenshots to progress the task. CRITICAL: You MUST ONLY use these EXACT function names and signatures: <c...
Please generate the next move according to the UI screenshot, instruction and previous actions. Instruction: I want to hire a CEO for a Generative AI comapny in US Previous actions: Step 1: type("I want to hire a CEO for a I want to hire a CEO for an AI company. Pl I want to hire a CEO for an AI company. Please give ...
<think> Ground truth action from DOM recording: click </think> <code> click(0.057, 0.026, "element") </code>
video_001
8
You are an expert GUI agent. You will be given a task, the history of previous actions, and two screenshots ('Before' and 'After'). Your goal is to determine the single user action that occurred between the two screenshots to progress the task. CRITICAL: You MUST ONLY use these EXACT function names and signatures: <c...
Please generate the next move according to the UI screenshot, instruction and previous actions. Instruction: I want to hire a CEO for a Generative AI comapny in US Previous actions: Step 1: type("I want to hire a CEO for a I want to hire a CEO for an AI company. Pl I want to hire a CEO for an AI company. Please give ...
<think> Ground truth action from DOM recording: click </think> <code> click(0.020, 0.011, "aria") </code>
video_001
9
You are an expert GUI agent. You will be given a task, the history of previous actions, and two screenshots ('Before' and 'After'). Your goal is to determine the single user action that occurred between the two screenshots to progress the task. CRITICAL: You MUST ONLY use these EXACT function names and signatures: <c...
Please generate the next move according to the UI screenshot, instruction and previous actions. Instruction: I want to hire a CEO for a Generative AI comapny in US Previous actions: Step 1: type("I want to hire a CEO for a I want to hire a CEO for an AI company. Pl I want to hire a CEO for an AI company. Please give ...
<think> Ground truth action from DOM recording: click </think> <code> click(0.041, 0.024, "aria") </code>
video_001
10
You are an expert GUI agent. You will be given a task, the history of previous actions, and two screenshots ('Before' and 'After'). Your goal is to determine the single user action that occurred between the two screenshots to progress the task. CRITICAL: You MUST ONLY use these EXACT function names and signatures: <c...
Please generate the next move according to the UI screenshot, instruction and previous actions. Instruction: I want to hire a CEO for a Generative AI comapny in US Previous actions: Step 1: type("I want to hire a CEO for a I want to hire a CEO for an AI company. Pl I want to hire a CEO for an AI company. Please give ...
<think> Ground truth action from DOM recording: click </think> <code> click(0.046, 0.002, "aria") </code>
video_001
11
You are an expert GUI agent. You will be given a task, the history of previous actions, and two screenshots ('Before' and 'After'). Your goal is to determine the single user action that occurred between the two screenshots to progress the task. CRITICAL: You MUST ONLY use these EXACT function names and signatures: <c...
Please generate the next move according to the UI screenshot, instruction and previous actions. Instruction: I want to hire a CEO for a Generative AI comapny in US Previous actions: Step 1: type("I want to hire a CEO for a I want to hire a CEO for an AI company. Pl I want to hire a CEO for an AI company. Please give ...
<think> Ground truth action from DOM recording: click </think> <code> click(0.017, 0.036, "aria") </code>
video_001
12
You are an expert GUI agent. You will be given a task, the history of previous actions, and two screenshots ('Before' and 'After'). Your goal is to determine the single user action that occurred between the two screenshots to progress the task. CRITICAL: You MUST ONLY use these EXACT function names and signatures: <c...
Please generate the next move according to the UI screenshot, instruction and previous actions. Instruction: I want to hire a CEO for a Generative AI comapny in US Previous actions: Step 1: type("I want to hire a CEO for a I want to hire a CEO for an AI company. Pl I want to hire a CEO for an AI company. Please give ...
<think> Ground truth action from DOM recording: click </think> <code> click(0.029, 0.016, "styles bentoCardContainer ajBKM") </code>
video_001
13
You are an expert GUI agent. You will be given a task, the history of previous actions, and two screenshots ('Before' and 'After'). Your goal is to determine the single user action that occurred between the two screenshots to progress the task. CRITICAL: You MUST ONLY use these EXACT function names and signatures: <c...
Please generate the next move according to the UI screenshot, instruction and previous actions. Instruction: I want to hire a CEO for a Generative AI comapny in US Previous actions: Step 1: type("I want to hire a CEO for a I want to hire a CEO for an AI company. Pl I want to hire a CEO for an AI company. Please give ...
<think> Ground truth action from DOM recording: click </think> <code> click(0.117, 0.009, "style personalInfoContainer jhG9q") </code>
video_001
14
You are an expert GUI agent. You will be given a task, the history of previous actions, and two screenshots ('Before' and 'After'). Your goal is to determine the single user action that occurred between the two screenshots to progress the task. CRITICAL: You MUST ONLY use these EXACT function names and signatures: <c...
Please generate the next move according to the UI screenshot, instruction and previous actions. Instruction: I want to hire a CEO for a Generative AI comapny in US Previous actions: Step 1: type("I want to hire a CEO for a I want to hire a CEO for an AI company. Pl I want to hire a CEO for an AI company. Please give ...
<think> Ground truth action from DOM recording: click </think> <code> click(0.014, 0.019, "aria") </code>
video_001
15
You are an expert GUI agent. You will be given a task, the history of previous actions, and two screenshots ('Before' and 'After'). Your goal is to determine the single user action that occurred between the two screenshots to progress the task. CRITICAL: You MUST ONLY use these EXACT function names and signatures: <c...
Please generate the next move according to the UI screenshot, instruction and previous actions. Instruction: I want to hire a CEO for a Generative AI comapny in US Previous actions: Step 1: type("I want to hire a CEO for a I want to hire a CEO for an AI company. Pl I want to hire a CEO for an AI company. Please give ...
<think> Ground truth action from DOM recording: click </think> <code> click(0.071, 0.032, "aria") </code>
video_001
16
You are an expert GUI agent. You will be given a task, the history of previous actions, and two screenshots ('Before' and 'After'). Your goal is to determine the single user action that occurred between the two screenshots to progress the task. CRITICAL: You MUST ONLY use these EXACT function names and signatures: <c...
Please generate the next move according to the UI screenshot, instruction and previous actions. Instruction: I want to hire a CEO for a Generative AI comapny in US Previous actions: Step 1: type("I want to hire a CEO for a I want to hire a CEO for an AI company. Pl I want to hire a CEO for an AI company. Please give ...
<think> Ground truth action from DOM recording: click </think> <code> click(0.061, 0.021, "aria") </code>
video_001
17
You are an expert GUI agent. You will be given a task, the history of previous actions, and two screenshots ('Before' and 'After'). Your goal is to determine the single user action that occurred between the two screenshots to progress the task. CRITICAL: You MUST ONLY use these EXACT function names and signatures: <c...
Please generate the next move according to the UI screenshot, instruction and previous actions. Instruction: I want to hire a CEO for a Generative AI comapny in US Previous actions: Step 1: type("I want to hire a CEO for a I want to hire a CEO for an AI company. Pl I want to hire a CEO for an AI company. Please give ...
<think> Ground truth action from DOM recording: click </think> <code> click(0.201, 0.030, "personViewTabsComponent Container") </code>
video_001
18
You are an expert GUI agent. You will be given a task, the history of previous actions, and two screenshots ('Before' and 'After'). Your goal is to determine the single user action that occurred between the two screenshots to progress the task. CRITICAL: You MUST ONLY use these EXACT function names and signatures: <c...
Please generate the next move according to the UI screenshot, instruction and previous actions. Instruction: I want to hire a CEO for a Generative AI comapny in US Previous actions: Step 1: type("I want to hire a CEO for a I want to hire a CEO for an AI company. Pl I want to hire a CEO for an AI company. Please give ...
<think> Ground truth action from DOM recording: click </think> <code> click(0.242, 0.031, "personViewTabsComponent Container") </code>
video_001
19
You are an expert GUI agent. You will be given a task, the history of previous actions, and two screenshots ('Before' and 'After'). Your goal is to determine the single user action that occurred between the two screenshots to progress the task. CRITICAL: You MUST ONLY use these EXACT function names and signatures: <c...
Please generate the next move according to the UI screenshot, instruction and previous actions. Instruction: I want to hire a CEO for a Generative AI comapny in US Previous actions: Step 1: type("I want to hire a CEO for a I want to hire a CEO for an AI company. Pl I want to hire a CEO for an AI company. Please give ...
<think> Ground truth action from DOM recording: click </think> <code> click(0.022, 0.023, "aria") </code>
video_001
20
You are an expert GUI agent. You will be given a task, the history of previous actions, and two screenshots ('Before' and 'After'). Your goal is to determine the single user action that occurred between the two screenshots to progress the task. CRITICAL: You MUST ONLY use these EXACT function names and signatures: <c...
Please generate the next move according to the UI screenshot, instruction and previous actions. Instruction: I want to hire a CEO for a Generative AI comapny in US Previous actions: Step 1: type("I want to hire a CEO for a I want to hire a CEO for an AI company. Pl I want to hire a CEO for an AI company. Please give ...
<think> Ground truth action from DOM recording: click </think> <code> click(0.014, 0.016, "element") </code>
video_001
21
You are an expert GUI agent. You will be given a task, the history of previous actions, and two screenshots ('Before' and 'After'). Your goal is to determine the single user action that occurred between the two screenshots to progress the task. CRITICAL: You MUST ONLY use these EXACT function names and signatures: <c...
Please generate the next move according to the UI screenshot, instruction and previous actions. Instruction: I want to hire a CEO for a Generative AI comapny in US Previous actions: Step 1: type("I want to hire a CEO for a I want to hire a CEO for an AI company. Pl I want to hire a CEO for an AI company. Please give ...
<think> Ground truth action from DOM recording: click </think> <code> click(0.014, 0.015, "styles personViewHeaderContainer TJ6js") </code>
video_001
22
You are an expert GUI agent. You will be given a task, the history of previous actions, and two screenshots ('Before' and 'After'). Your goal is to determine the single user action that occurred between the two screenshots to progress the task. CRITICAL: You MUST ONLY use these EXACT function names and signatures: <c...
Please generate the next move according to the UI screenshot, instruction and previous actions. Instruction: I want to hire a CEO for a Generative AI comapny in US Previous actions: Step 1: type("I want to hire a CEO for a I want to hire a CEO for an AI company. Pl I want to hire a CEO for an AI company. Please give ...
<think> Ground truth action from DOM recording: click </think> <code> click(0.006, 0.010, "d408a673 ff79 431f bdd2 ee8dc791a175") </code>
video_001
23
You are an expert GUI agent. You will be given a task, the history of previous actions, and two screenshots ('Before' and 'After'). Your goal is to determine the single user action that occurred between the two screenshots to progress the task. CRITICAL: You MUST ONLY use these EXACT function names and signatures: <c...
Please generate the next move according to the UI screenshot, instruction and previous actions. Instruction: I want to hire a CEO for a Generative AI comapny in US Previous actions: Step 1: type("I want to hire a CEO for a I want to hire a CEO for an AI company. Pl I want to hire a CEO for an AI company. Please give ...
<think> Ground truth action from DOM recording: click </think> <code> click(0.055, 0.015, "div") </code>
video_001
24
You are an expert GUI agent. You will be given a task, the history of previous actions, and two screenshots ('Before' and 'After'). Your goal is to determine the single user action that occurred between the two screenshots to progress the task. CRITICAL: You MUST ONLY use these EXACT function names and signatures: <c...
Please generate the next move according to the UI screenshot, instruction and previous actions. Instruction: I want to hire a CEO for a Generative AI comapny in US Previous actions: Step 1: type("I want to hire a CEO for a I want to hire a CEO for an AI company. Pl I want to hire a CEO for an AI company. Please give ...
<think> Ground truth action from DOM recording: click </think> <code> click(0.032, 0.006, "element") </code>
video_001
25
You are an expert GUI agent. You will be given a task, the history of previous actions, and two screenshots ('Before' and 'After'). Your goal is to determine the single user action that occurred between the two screenshots to progress the task. CRITICAL: You MUST ONLY use these EXACT function names and signatures: <c...
Please generate the next move according to the UI screenshot, instruction and previous actions. Instruction: I want to hire a CEO for a Generative AI comapny in US Previous actions: Step 1: type("I want to hire a CEO for a I want to hire a CEO for an AI company. Pl I want to hire a CEO for an AI company. Please give ...
<think> Ground truth action from DOM recording: click </think> <code> click(0.029, 0.021, "aria") </code>
video_001
26
You are an expert GUI agent. You will be given a task, the history of previous actions, and two screenshots ('Before' and 'After'). Your goal is to determine the single user action that occurred between the two screenshots to progress the task. CRITICAL: You MUST ONLY use these EXACT function names and signatures: <c...
Please generate the next move according to the UI screenshot, instruction and previous actions. Instruction: I want to hire a CEO for a Generative AI comapny in US Previous actions: Step 1: type("I want to hire a CEO for a I want to hire a CEO for an AI company. Pl I want to hire a CEO for an AI company. Please give ...
<think> Ground truth action from DOM recording: click </think> <code> click(0.006, 0.013, "styles personViewHeaderContainer TJ6js") </code>
video_001
27
You are an expert GUI agent. You will be given a task, the history of previous actions, and two screenshots ('Before' and 'After'). Your goal is to determine the single user action that occurred between the two screenshots to progress the task. CRITICAL: You MUST ONLY use these EXACT function names and signatures: <c...
Please generate the next move according to the UI screenshot, instruction and previous actions. Instruction: I want to hire a CEO for a Generative AI comapny in US Previous actions: Step 1: type("I want to hire a CEO for a I want to hire a CEO for an AI company. Pl I want to hire a CEO for an AI company. Please give ...
<think> Ground truth action from DOM recording: click </think> <code> click(0.072, 0.016, "div") </code>
video_001
28
You are an expert GUI agent. You will be given a task, the history of previous actions, and two screenshots ('Before' and 'After'). Your goal is to determine the single user action that occurred between the two screenshots to progress the task. CRITICAL: You MUST ONLY use these EXACT function names and signatures: <c...
Please generate the next move according to the UI screenshot, instruction and previous actions. Instruction: I want to hire a CEO for a Generative AI comapny in US Previous actions: Step 1: type("I want to hire a CEO for a I want to hire a CEO for an AI company. Pl I want to hire a CEO for an AI company. Please give ...
<think> Ground truth action from DOM recording: click </think> <code> click(0.037, 0.018, "aria") </code>
video_001
29
You are an expert GUI agent. You will be given a task, the history of previous actions, and two screenshots ('Before' and 'After'). Your goal is to determine the single user action that occurred between the two screenshots to progress the task. CRITICAL: You MUST ONLY use these EXACT function names and signatures: <c...
Please generate the next move according to the UI screenshot, instruction and previous actions. Instruction: I want to hire a CEO for a Generative AI comapny in US Previous actions: Step 1: type("I want to hire a CEO for a I want to hire a CEO for an AI company. Pl I want to hire a CEO for an AI company. Please give ...
<think> Ground truth action from DOM recording: click </think> <code> click(0.015, 0.033, "element") </code>
video_001
30
You are an expert GUI agent. You will be given a task, the history of previous actions, and two screenshots ('Before' and 'After'). Your goal is to determine the single user action that occurred between the two screenshots to progress the task. CRITICAL: You MUST ONLY use these EXACT function names and signatures: <c...
Please generate the next move according to the UI screenshot, instruction and previous actions. Instruction: I want to hire a CEO for a Generative AI comapny in US Previous actions: Step 1: type("I want to hire a CEO for a I want to hire a CEO for an AI company. Pl I want to hire a CEO for an AI company. Please give ...
<think> Ground truth action from DOM recording: click </think> <code> click(0.032, 0.023, "style isViewedlabelContainer Pyc t") </code>
video_001
31
You are an expert GUI agent. You will be given a task, the history of previous actions, and two screenshots ('Before' and 'After'). Your goal is to determine the single user action that occurred between the two screenshots to progress the task. CRITICAL: You MUST ONLY use these EXACT function names and signatures: <c...
Please generate the next move according to the UI screenshot, instruction and previous actions. Instruction: I want to hire a CEO for a Generative AI comapny in US Previous actions: Step 1: type("I want to hire a CEO for a I want to hire a CEO for an AI company. Pl I want to hire a CEO for an AI company. Please give ...
<think> Ground truth action from DOM recording: click </think> <code> click(0.011, 0.016, "b4fee2d6 f01d 4199 a8bb 0e9d6be01af1") </code>
video_001
32
You are an expert GUI agent. You will be given a task, the history of previous actions, and two screenshots ('Before' and 'After'). Your goal is to determine the single user action that occurred between the two screenshots to progress the task. CRITICAL: You MUST ONLY use these EXACT function names and signatures: <c...
Please generate the next move according to the UI screenshot, instruction and previous actions. Instruction: I want to hire a CEO for a Generative AI comapny in US Previous actions: Step 1: type("I want to hire a CEO for a I want to hire a CEO for an AI company. Pl I want to hire a CEO for an AI company. Please give ...
<think> Ground truth action from DOM recording: click </think> <code> click(0.083, 0.007, "div") </code>
video_001
33
You are an expert GUI agent. You will be given a task, the history of previous actions, and two screenshots ('Before' and 'After'). Your goal is to determine the single user action that occurred between the two screenshots to progress the task. CRITICAL: You MUST ONLY use these EXACT function names and signatures: <c...
Please generate the next move according to the UI screenshot, instruction and previous actions. Instruction: I want to hire a CEO for a Generative AI comapny in US Previous actions: Step 1: type("I want to hire a CEO for a I want to hire a CEO for an AI company. Pl I want to hire a CEO for an AI company. Please give ...
<think> Ground truth action from DOM recording: click </think> <code> click(0.037, 0.012, "styles bentoCardContainer ajBKM") </code>
video_001
34
You are an expert GUI agent. You will be given a task, the history of previous actions, and two screenshots ('Before' and 'After'). Your goal is to determine the single user action that occurred between the two screenshots to progress the task. CRITICAL: You MUST ONLY use these EXACT function names and signatures: <c...
Please generate the next move according to the UI screenshot, instruction and previous actions. Instruction: I want to hire a CEO for a Generative AI comapny in US Previous actions: Step 1: type("I want to hire a CEO for a I want to hire a CEO for an AI company. Pl I want to hire a CEO for an AI company. Please give ...
<think> Ground truth action from DOM recording: click </think> <code> click(0.125, 0.183, "styles personalInfoContainer gUhdJ") </code>
video_001
35
You are an expert GUI agent. You will be given a task, the history of previous actions, and two screenshots ('Before' and 'After'). Your goal is to determine the single user action that occurred between the two screenshots to progress the task. CRITICAL: You MUST ONLY use these EXACT function names and signatures: <c...
Please generate the next move according to the UI screenshot, instruction and previous actions. Instruction: I want to hire a CEO for a Generative AI comapny in US Previous actions: Step 1: type("I want to hire a CEO for a I want to hire a CEO for an AI company. Pl I want to hire a CEO for an AI company. Please give ...
<think> Ground truth action from DOM recording: click </think> <code> click(0.029, 0.007, "aria") </code>
video_001
36
You are an expert GUI agent. You will be given a task, the history of previous actions, and two screenshots ('Before' and 'After'). Your goal is to determine the single user action that occurred between the two screenshots to progress the task. CRITICAL: You MUST ONLY use these EXACT function names and signatures: <c...
Please generate the next move according to the UI screenshot, instruction and previous actions. Instruction: I want to hire a CEO for a Generative AI comapny in US Previous actions: Step 1: type("I want to hire a CEO for a I want to hire a CEO for an AI company. Pl I want to hire a CEO for an AI company. Please give ...
<think> Ground truth action from DOM recording: click </think> <code> click(0.060, 0.007, "aria") </code>
video_001
37
You are an expert GUI agent. You will be given a task, the history of previous actions, and two screenshots ('Before' and 'After'). Your goal is to determine the single user action that occurred between the two screenshots to progress the task. CRITICAL: You MUST ONLY use these EXACT function names and signatures: <c...
Please generate the next move according to the UI screenshot, instruction and previous actions. Instruction: I want to hire a CEO for a Generative AI comapny in US Previous actions: Step 1: type("I want to hire a CEO for a I want to hire a CEO for an AI company. Pl I want to hire a CEO for an AI company. Please give ...
<think> Ground truth action from DOM recording: click </think> <code> click(0.011, 0.015, "element") </code>
video_001
38
You are an expert GUI agent. You will be given a task, the history of previous actions, and two screenshots ('Before' and 'After'). Your goal is to determine the single user action that occurred between the two screenshots to progress the task. CRITICAL: You MUST ONLY use these EXACT function names and signatures: <c...
Please generate the next move according to the UI screenshot, instruction and previous actions. Instruction: I want to hire a CEO for a Generative AI comapny in US Previous actions: Step 1: type("I want to hire a CEO for a I want to hire a CEO for an AI company. Pl I want to hire a CEO for an AI company. Please give ...
<think> Ground truth action from DOM recording: click </think> <code> click(0.021, 0.022, "element") </code>
video_001
39
You are an expert GUI agent. You will be given a task, the history of previous actions, and two screenshots ('Before' and 'After'). Your goal is to determine the single user action that occurred between the two screenshots to progress the task. CRITICAL: You MUST ONLY use these EXACT function names and signatures: <c...
Please generate the next move according to the UI screenshot, instruction and previous actions. Instruction: I want to hire a CEO for a Generative AI comapny in US Previous actions: Step 1: type("I want to hire a CEO for a I want to hire a CEO for an AI company. Pl I want to hire a CEO for an AI company. Please give ...
<think> Ground truth action from DOM recording: click </think> <code> click(0.060, 0.039, "aria") </code>
video_001
40
You are an expert GUI agent. You will be given a task, the history of previous actions, and two screenshots ('Before' and 'After'). Your goal is to determine the single user action that occurred between the two screenshots to progress the task. CRITICAL: You MUST ONLY use these EXACT function names and signatures: <c...
Please generate the next move according to the UI screenshot, instruction and previous actions. Instruction: I want to hire a CEO for a Generative AI comapny in US Previous actions: Step 1: type("I want to hire a CEO for a I want to hire a CEO for an AI company. Pl I want to hire a CEO for an AI company. Please give ...
<think> Ground truth action from DOM recording: click </think> <code> click(0.171, 0.041, "aria") </code>
video_001
41
You are an expert GUI agent. You will be given a task, the history of previous actions, and two screenshots ('Before' and 'After'). Your goal is to determine the single user action that occurred between the two screenshots to progress the task. CRITICAL: You MUST ONLY use these EXACT function names and signatures: <c...
Please generate the next move according to the UI screenshot, instruction and previous actions. Instruction: I want to hire a CEO for a Generative AI comapny in US Previous actions: Step 1: type("I want to hire a CEO for a I want to hire a CEO for an AI company. Pl I want to hire a CEO for an AI company. Please give ...
<think> The user typed the text: 'CEO Candidates for AI company' </think> <code> type("CEO Candidates for AI company") </code>
video_001
42
You are an expert GUI agent. You will be given a task, the history of previous actions, and two screenshots ('Before' and 'After'). Your goal is to determine the single user action that occurred between the two screenshots to progress the task. CRITICAL: You MUST ONLY use these EXACT function names and signatures: <c...
Please generate the next move according to the UI screenshot, instruction and previous actions. Instruction: I want to hire a CEO for a Generative AI comapny in US Previous actions: Step 1: type("I want to hire a CEO for a I want to hire a CEO for an AI company. Pl I want to hire a CEO for an AI company. Please give ...
<think> Ground truth action from DOM recording: click </think> <code> click(0.070, 0.007, "aria") </code>
video_001
43
You are an expert GUI agent. You will be given a task, the history of previous actions, and two screenshots ('Before' and 'After'). Your goal is to determine the single user action that occurred between the two screenshots to progress the task. CRITICAL: You MUST ONLY use these EXACT function names and signatures: <c...
Please generate the next move according to the UI screenshot, instruction and previous actions. Instruction: I want to hire a CEO for a Generative AI comapny in US Previous actions: Step 1: type("I want to hire a CEO for a I want to hire a CEO for an AI company. Pl I want to hire a CEO for an AI company. Please give ...
<think> Ground truth action from DOM recording: click </think> <code> click(0.075, 0.031, "aria") </code>
video_001
44
You are an expert GUI agent. You will be given a task, the history of previous actions, and two screenshots ('Before' and 'After'). Your goal is to determine the single user action that occurred between the two screenshots to progress the task. CRITICAL: You MUST ONLY use these EXACT function names and signatures: <c...
Please generate the next move according to the UI screenshot, instruction and previous actions. Instruction: I want to hire a CEO for a Generative AI comapny in US Previous actions: Step 1: type("I want to hire a CEO for a I want to hire a CEO for an AI company. Pl I want to hire a CEO for an AI company. Please give ...
<think> The change between the 'Before' and 'After' screenshots is in the "Company" filter section. In the 'Before' screenshot, the company filter is empty, while in the 'After' screenshot, it includes "OpenAI," "Runway," "Stability AI," and "Midjourney." This indicates that a user action added these companies to the f...
video_001
45
You are an expert GUI agent. You will be given a task, the history of previous actions, and two screenshots ('Before' and 'After'). Your goal is to determine the single user action that occurred between the two screenshots to progress the task. CRITICAL: You MUST ONLY use these EXACT function names and signatures: <c...
Please generate the next move according to the UI screenshot, instruction and previous actions. Instruction: I want to hire a CEO for a Generative AI comapny in US Previous actions: Step 1: type("I want to hire a CEO for a I want to hire a CEO for an AI company. Pl I want to hire a CEO for an AI company. Please give ...
<think> The change between the 'Before' and 'After' screenshots is the increase in the progress bar from 24% to 30% and the change in the company filter from "5 more" to "14 more". This suggests that an additional filter was applied, likely by expanding the company filter options. </think> <code> click(0.029, 0.016, "s...
video_001
46
You are an expert GUI agent. You will be given a task, the history of previous actions, and two screenshots ('Before' and 'After'). Your goal is to determine the single user action that occurred between the two screenshots to progress the task. CRITICAL: You MUST ONLY use these EXACT function names and signatures: <c...
Please generate the next move according to the UI screenshot, instruction and previous actions. Instruction: I want to hire a CEO for a Generative AI comapny in US Previous actions: Step 1: type("I want to hire a CEO for a I want to hire a CEO for an AI company. Pl I want to hire a CEO for an AI company. Please give ...
<think> The only change between the 'Before' and 'After' screenshots is the increase in the number of companies from "43 more" to "53 more" under the "Company" filter. This suggests that a user action added more companies to the filter. </think> <code> click(0.5, 0.5, "Add Company Filter") </code>
video_001
47
You are an expert GUI agent. You will be given a task, the history of previous actions, and two screenshots ('Before' and 'After'). Your goal is to determine the single user action that occurred between the two screenshots to progress the task. CRITICAL: You MUST ONLY use these EXACT function names and signatures: <c...
Please generate the next move according to the UI screenshot, instruction and previous actions. Instruction: I want to hire a CEO for a Generative AI comapny in US Previous actions: Step 1: type("I want to hire a CEO for a I want to hire a CEO for an AI company. Pl I want to hire a CEO for an AI company. Please give ...
<think> The "Before" screenshot shows a search interface with filters applied, displaying 106 results. The "After" screenshot shows an empty interface with no results or filters visible. This suggests that the user action cleared the search results and filters. </think> <code> click(0.5, 0.5, "Clear Filters") </code>
video_001
48
You are an expert GUI agent. You will be given a task, the history of previous actions, and two screenshots ('Before' and 'After'). Your goal is to determine the single user action that occurred between the two screenshots to progress the task. CRITICAL: You MUST ONLY use these EXACT function names and signatures: <c...
Please generate the next move according to the UI screenshot, instruction and previous actions. Instruction: I want to hire a CEO for a Generative AI comapny in US Previous actions: Step 1: type("I want to hire a CEO for a I want to hire a CEO for an AI company. Pl I want to hire a CEO for an AI company. Please give ...
<think> The 'Before' screenshot shows a blank search interface with a prompt input field. The 'After' screenshot displays search results for potential CEO candidates, indicating that a search was performed. The transformation likely occurred due to a click on the search button after entering a query. </think> <code> cl...
video_001
49
You are an expert GUI agent. You will be given a task, the history of previous actions, and two screenshots ('Before' and 'After'). Your goal is to determine the single user action that occurred between the two screenshots to progress the task. CRITICAL: You MUST ONLY use these EXACT function names and signatures: <c...
Please generate the next move according to the UI screenshot, instruction and previous actions. Instruction: I want to hire a CEO for a Generative AI comapny in US Previous actions: Step 1: type("I want to hire a CEO for a I want to hire a CEO for an AI company. Pl I want to hire a CEO for an AI company. Please give ...
<think> The change between the 'Before' and 'After' screenshots is the addition of company logos next to the company names in the experience section of the profiles. This suggests that a user action enabled the display of these logos. </think> <code> click(0.041, 0.024, "aria") </code>
video_001
50
You are an expert GUI agent. You will be given a task, the history of previous actions, and two screenshots ('Before' and 'After'). Your goal is to determine the single user action that occurred between the two screenshots to progress the task. CRITICAL: You MUST ONLY use these EXACT function names and signatures: <c...
Please generate the next move according to the UI screenshot, instruction and previous actions. Instruction: I want to hire a CEO for a Generative AI comapny in US Previous actions: Step 1: type("I want to hire a CEO for a I want to hire a CEO for an AI company. Pl I want to hire a CEO for an AI company. Please give ...
<think> The change between the 'Before' and 'After' screenshots is the appearance of a profile picture for the second candidate, Vikram Chalana. This suggests that the user clicked on an element that triggered the loading or display of the profile picture. </think> <code> click(0.125, 0.183, "styles personalInfoContain...
video_001
51
You are an expert GUI agent. You will be given a task, the history of previous actions, and two screenshots ('Before' and 'After'). Your goal is to determine the single user action that occurred between the two screenshots to progress the task. CRITICAL: You MUST ONLY use these EXACT function names and signatures: <c...
Please generate the next move according to the UI screenshot, instruction and previous actions. Instruction: I want to hire a CEO for a Generative AI comapny in US Previous actions: Step 1: type("I want to hire a CEO for a I want to hire a CEO for an AI company. Pl I want to hire a CEO for an AI company. Please give ...
<think> The transformation from the 'Before' to the 'After' screenshot shows that the user has navigated from a list of profiles to a detailed view of a specific profile. This change indicates that the user clicked on the "View Full Profile" button for the first profile in the list. </think> <code> click(0.5, 0.5, "Vie...
End of preview. Expand in Data Studio

UI Automation Dataset (Multi-Video)

106 examples from 1 videos - UI automation tasks from screen recordings.

Dataset Structure

Each entry contains:

  • video_id: Sequential ID for each video (video_001, video_002, etc.)
  • step: Step number within that video (0, 1, 2, ...)
  • system: System prompt for the GUI agent
  • user: Task instruction + previous actions
  • assistant: Model's reasoning and action
  • image: Screenshot of the UI state

Usage

from datasets import load_dataset

ds = load_dataset("KMH158-QLU/test_dataset_16")

# Access by video
for video_id in set(ds['train']['video_id']):
    video_data = ds['train'].filter(lambda x: x['video_id'] == video_id)
    print(f"Video {video_id}: {len(video_data)} steps")

# Or iterate all examples
for item in ds['train']:
    print(f"{item['video_id']} - Step {item['step']}: {item['assistant'][:50]}...")

Growing Dataset

This dataset supports multiple videos. Each video gets a unique ID (video_001, video_002, etc.). New videos are automatically appended with the next available ID.

Downloads last month
16