Files
sci-gui-agent-benchmark/evaluation_examples/examples/libreoffice_calc/01b269ae-2111-4a07-81fd-3fcd711993b0.json
Danyang Zhang afd5952e44 ver Oct3rd (#349)
updated a series of instructions to ask the agent not to do any
unnecessary actions.
2025-10-04 00:13:29 +08:00

86 lines
2.2 KiB
JSON

{
"id": "01b269ae-2111-4a07-81fd-3fcd711993b0",
"snapshot": "libreoffice_calc",
"instruction": "Fill all the blank cells in B1:E30 with the value in the cell above it. Finish the work and don't touch irrelevant regions, even if they are blank.",
"source": "https://www.youtube.com/shorts/VrUzPTIwQ04",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/libreoffice_calc/01b269ae-2111-4a07-81fd-3fcd711993b0/Student_Level_Fill_Blank.xlsx",
"path": "/home/user/Student_Level_Fill_Blank.xlsx"
}
]
}
},
{
"type": "open",
"parameters": {
"path": "/home/user/Student_Level_Fill_Blank.xlsx"
}
}
],
"trajectory": "trajectories/01b269ae-2111-4a07-81fd-3fcd711993b0",
"related_apps": [
"libreoffice calc"
],
"evaluator": {
"postconfig": [
{
"type": "activate_window",
"parameters": {
"window_name": "Student_Level_Fill_Blank.xlsx - LibreOffice Calc",
"strict": true
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
},
{
"type": "execute",
"parameters": {
"command": [
"python",
"-c",
"import pyautogui; pyautogui.hotkey(\"ctrl\", \"s\");"
]
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
}
],
"func": "compare_table",
"expected": {
"type": "cloud_file",
"path": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/libreoffice_calc/01b269ae-2111-4a07-81fd-3fcd711993b0/Student_Level_Fill_Blank_gold.xlsx",
"dest": "Student_Level_Fill_Blank_gold.xlsx"
},
"result": {
"type": "vm_file",
"path": "/home/user/Student_Level_Fill_Blank.xlsx",
"dest": "Student_Level_Fill_Blank.xlsx"
},
"options": {
"rules": [
{
"type": "sheet_data",
"sheet_idx0": 0,
"sheet_idx1": "EI0"
}
]
}
},
"proxy": false,
"fixed_ip": false,
"possibility_of_env_change": "low"
}