lzy/sci-gui-agent-benchmark
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

update pptc as libreoffice impress

Browse Source
This commit is contained in:
tsuky_chen
2024-02-15 01:51:34 +08:00
parent f7bb33724c 8d69eec68f
commit dd1644b3f4
15 changed files with 442 additions and 140 deletions
Download Patch File Download Diff File Expand all files Collapse all files

19
evaluation_examples/examples/chrome/3720f614-37fd-4d04-8a6b-76f54f8c222d.json Normal file
View File

@@ -0,0 +1,19 @@
{
"id": "3720f614-37fd-4d04-8a6b-76f54f8c222d",
"snapshot": "chrome",
"instruction": "I am more familiar with Korean as I am from Korea. I want to use chrome with my mother tongue. Could you help me change the Chrome interface language to Korean? ",
"source": "https://superuser.com/questions/984668/change-interface-language-of-chrome-to-english",
"config": [
],
"trajectory": "trajectories/",
"related_apps": [
"chrome"
],
"evaluator": {
"func": "infeasible",
"result": {
},
"expected": {
}
}
}

207
evaluation_examples/examples/chrome/44ee5668-ecd5-4366-a6ce-c1c9b8d4e938.json
View File

@@ -4,6 +4,213 @@
"instruction": "I am looking for an website address I accessed a month ago, but Youtube websites which take almost all of my browsing history are interrupting my search. This is too annoying. I want to remove all my Youtube browsing history first to facilitate my search. Could you help me clear browsing history from Youtube?",
"source": "https://superuser.com/questions/1787991/clear-browsing-history-from-specific-site-on-chrome",
"config": [
{
"type": "update_browse_history",
"parameters": {
"history": [
{
"url": "https://www.youtube.com/watch?v=dQw4w9WgXcQ",
"title": "Rick Astley - Never Gonna Give You Up (Official Music Video)",
"visit_time_from_now_in_seconds": 3600
},
{
"url": "https://www.youtube.com/watch?v=9bZkp7q19f0",
"title": "PSY - GANGNAM STYLE(강남스타일) M/V",
"visit_time_from_now_in_seconds": 1631
},
{
"url": "https://www.youtube.com/watch?v=3tmd-ClpJxA",
"title": "Maroon 5 - Sugar (Official Music Video)",
"visit_time_from_now_in_seconds": 900
},
{
"url": "https://www.nytimes.com/",
"title": "The New York Times",
"visit_time_from_now_in_seconds": 300
},
{
"url": "https://www.youtube.com/watch?v=OPf0YbXqDm0",
"title": "Ed Sheeran - Shape of You [Official Music Video]",
"visit_time_from_now_in_seconds": 1200
},
{
"url": "https://www.youtube.com/watch?v=JGwWNGJdvx8",
"title": "Taylor Swift - Shake It Off",
"visit_time_from_now_in_seconds": 2400
},
{
"url": "https://www.bbc.co.uk/",
"title": "BBC",
"visit_time_from_now_in_seconds": 1500
},
{
"url": "https://www.youtube.com/watch?v=2Vv-BfVoq4g",
"title": "Adele - Hello",
"visit_time_from_now_in_seconds": 1800
},
{
"url": "https://www.youtube.com/watch?v=YQHsXMglC9A",
"title": "Katy Perry - Roar (Official Music Video)",
"visit_time_from_now_in_seconds": 2100
},
{
"url": "https://www.cnn.com/",
"title": "CNN",
"visit_time_from_now_in_seconds": 2700
},
{
"url": "https://www.youtube.com/watch?v=ru0K8uYEZWw",
"title": "Justin Bieber - Baby ft. Ludacris (Official Music Video)",
"visit_time_from_now_in_seconds": 3200
},
{
"url": "https://www.youtube.com/watch?v=9bZkp7q19f0",
"title": "PSY - GANGNAM STYLE(강남스타일) M/V",
"visit_time_from_now_in_seconds": 3700
},
{
"url": "https://www.nationalgeographic.com/",
"title": "National Geographic",
"visit_time_from_now_in_seconds": 4000
},
{
"url": "https://www.youtube.com/watch?v=OPf0YbXqDm0",
"title": "Ed Sheeran - Shape of You [Official Music Video]",
"visit_time_from_now_in_seconds": 4300
},
{
"url": "https://www.youtube.com/watch?v=JGwWNGJdvx8",
"title": "Taylor Swift - Shake It Off",
"visit_time_from_now_in_seconds": 4700
},
{
"url": "https://www.bbc.co.uk/",
"title": "BBC",
"visit_time_from_now_in_seconds": 5000
},
{
"url": "https://www.youtube.com/watch?v=2Vv-BfVoq4g",
"title": "Adele - Hello",
"visit_time_from_now_in_seconds": 5300
},
{
"url": "https://www.youtube.com/watch?v=YQHsXMglC9A",
"title": "Katy Perry - Roar (Official Music Video)",
"visit_time_from_now_in_seconds": 5600
},
{
"url": "https://www.cnn.com/",
"title": "CNN",
"visit_time_from_now_in_seconds": 5900
},
{
"url": "https://www.youtube.com/watch?v=ru0K8uYEZWw",
"title": "Justin Bieber - Baby ft. Ludacris (Official Music Video)",
"visit_time_from_now_in_seconds": 6300
},
{
"url": "https://www.youtube.com/watch?v=dQw4w9WgXcQ",
"title": "Rick Astley - Never Gonna Give You Up (Official Music Video)",
"visit_time_from_now_in_seconds": 6700
},
{
"url": "https://www.nationalgeographic.com/",
"title": "National Geographic",
"visit_time_from_now_in_seconds": 7000
},
{
"url": "https://www.youtube.com/watch?v=OPf0YbXqDm0",
"title": "Ed Sheeran - Shape of You [Official Music Video]",
"visit_time_from_now_in_seconds": 7300
},
{
"url": "https://www.youtube.com/watch?v=JGwWNGJdvx8",
"title": "Taylor Swift - Shake It Off",
"visit_time_from_now_in_seconds": 7600
},
{
"url": "https://www.bbc.co.uk/",
"title": "BBC",
"visit_time_from_now_in_seconds": 7900
},
{
"url": "https://www.youtube.com/watch?v=2Vv-BfVoq4g",
"title": "Adele - Hello",
"visit_time_from_now_in_seconds": 8200
},
{
"url": "https://www.youtube.com/watch?v=YQHsXMglC9A",
"title": "Katy Perry - Roar (Official Music Video)",
"visit_time_from_now_in_seconds": 8500
},
{
"url": "https://www.cnn.com/",
"title": "CNN",
"visit_time_from_now_in_seconds": 8800
},
{
"url": "https://www.youtube.com/watch?v=ru0K8uYEZWw",
"title": "Justin Bieber - Baby ft. Ludacris (Official Music Video)",
"visit_time_from_now_in_seconds": 9100
},
{
"url": "https://www.youtube.com/watch?v=dQw4w9WgXcQ",
"title": "Rick Astley - Never Gonna Give You Up (Official Music Video)",
"visit_time_from_now_in_seconds": 9400
},
{
"url": "https://www.nationalgeographic.com/",
"title": "National Geographic",
"visit_time_from_now_in_seconds": 9700
},
{
"url": "https://www.youtube.com/watch?v=OPf0YbXqDm0",
"title": "Ed Sheeran - Shape of You [Official Music Video]",
"visit_time_from_now_in_seconds": 10000
},
{
"url": "https://www.youtube.com/watch?v=JGwWNGJdvx8",
"title": "Taylor Swift - Shake It Off",
"visit_time_from_now_in_seconds": 10300
},
{
"url": "https://www.bbc.co.uk/",
"title": "BBC",
"visit_time_from_now_in_seconds": 10600
},
{
"url": "https://www.youtube.com/watch?v=2Vv-BfVoq4g",
"title": "Adele - Hello",
"visit_time_from_now_in_seconds": 10900
},
{
"url": "https://www.youtube.com/watch?v=YQHsXMglC9A",
"title": "Katy Perry - Roar (Official Music Video)",
"visit_time_from_now_in_seconds": 11200
},
{
"url": "https://www.cnn.com/",
"title": "CNN",
"visit_time_from_now_in_seconds": 11500
},
{
"url": "https://www.youtube.com/watch?v=ru0K8uYEZWw",
"title": "Justin Bieber - Baby ft. Ludacris (Official Music Video)",
"visit_time_from_now_in_seconds": 11800
},
{
"url": "https://www.youtube.com/watch?v=dQw4w9WgXcQ",
"title": "Rick Astley - Never Gonna Give You Up (Official Music Video)",
"visit_time_from_now_in_seconds": 12100
},
{
"url": "https://www.nationalgeographic.com/",
"title": "National Geographic",
"visit_time_from_now_in_seconds": 12400
}
]
}
},
{
"type": "launch",
"parameters": {

19
evaluation_examples/examples/chrome/93eabf48-6a27-4cb6-b963-7d5fe1e0d3a9.json Normal file
View File

@@ -0,0 +1,19 @@
{
"id": "93eabf48-6a27-4cb6-b963-7d5fe1e0d3a9",
"snapshot": "chrome",
"instruction": "Could you assist me in turning off the dark mode feature in Google Chrome? I've noticed that while dark mode is great for reducing glare, it actually makes it more challenging for me to read text clearly, especially with my astigmatism.",
"source": "https://superuser.com/questions/1417973/how-to-disable-google-chrome-dark-mode",
"config": [
],
"trajectory": "trajectories/",
"related_apps": [
"chrome"
],
"evaluator": {
"func": "infeasible",
"result": {
},
"expected": {
}
}
}

26
evaluation_examples/examples/chrome/ae78f875-5b98-4907-bbb5-9c737fc68c03.json
View File

@@ -4,40 +4,16 @@
"instruction": "Could you please change the number of search results displayed on one page to 50? I find that having more results visible at once significantly enhances my research efficiency, as it reduces the need to constantly click through multiple pages. ",
"source": "https://support.google.com/chrome/thread/219988391/increase-search-results-per-page?hl=en",
"config": [
{
"type": "launch",
"parameters": {
"command": [
"google-chrome",
"--remote-debugging-port=1337"
]
}
},
{
"type": "launch",
"parameters": {
"command": [
"socat",
"tcp-listen:9222,fork",
"tcp:localhost:1337"
]
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"chrome"
],
"evaluator": {
"func": "exact_match",
"func": "infeasible",
"result": {
"type": "number_of_search_results"
},
"expected": {
"type": "rule",
"rules": {
"expected": 50
}
}
}
}

66
evaluation_examples/examples/libreoffice_calc/2bd59342-0664-4ccb-ba87-79379096cc08.json
View File

@@ -4,78 +4,16 @@
"instruction": "Make sparkline chart line by line",
"source": "https://www.youtube.com/shorts/L3Z-F1QTQFY",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://drive.usercontent.google.com/download?id=1uywX5XWMvesnb4-8LPKEzr2HFU7HmoIu&export=download&authuser=0&confirm=t&uuid=267bfe49-a861-4272-ae7c-39c95df35e84&at=APZUnTUbs-FF06hSMv3yWfdXc02l:1703508870351",
"path": "/home/user/OrderId_Month_Chart.xlsx"
}
]
}
},
{
"type": "open",
"parameters": {
"path": "/home/user/OrderId_Month_Chart.xlsx"
}
}
],
"trajectory": "trajectories/2bd59342-0664-4ccb-ba87-79379096cc08",
"related_apps": [
"libreoffice calc"
"libreoffice_calc"
],
"evaluator": {
"postconfig": [
{
"type": "activate_window",
"parameters": {
"window_name": "OrderId_Month_Chart.xlsx - LibreOffice Calc",
"strict": true
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
},
{
"type": "execute",
"parameters": {
"command": [
"python",
"-c",
"import pyautogui; pyautogui.hotkey(\"ctrl\", \"s\");"
]
}
}
],
"func": "compare_table",
"func": "infeasible",
"expected": {
"type": "cloud_file",
"path": "https://drive.usercontent.google.com/download?id=1KQJJLVPGtTL_7ArEWvwwbFbJSiA3cgSE&export=download&authuser=0&confirm=t&uuid=6b11c721-caad-439a-b369-4c13c7a485df&at=APZUnTV5-1isKrDKSHV9NeJ6TDeS:1703509054094",
"dest": "OrderId_Month_Chart_gold.xlsx"
},
"result": {
"type": "vm_file",
"path": "/home/user/OrderId_Month_Chart.xlsx",
"dest": "OrderId_Month_Chart.xlsx"
},
"options": {
"rules": [
{
"type": "sparkline",
"sheet_idx0": 0,
"sheet_idx1": "EI0"
},
{
"type": "sheet_data",
"sheet_idx0": 0,
"sheet_idx1": "EI0"
}
]
}
}
}

19
evaluation_examples/examples/libreoffice_calc/7b802dad-6e0f-4204-9815-d4e3f57627d8.json Normal file
View File

@@ -0,0 +1,19 @@
{
"id": "7b802dad-6e0f-4204-9815-d4e3f57627d8",
"snapshot": "libreoffice_calc",
"instruction": "I would like to sort this table based on cell color, placing all the rows marked with pink at the beginning, while keeping their order among themselves unchanged.",
"source": "https://www.youtube.com/shorts/Of-lzeP1usE",
"config": [
],
"trajectory": "trajectories/7b802dad-6e0f-4204-9815-d4e3f57627d8",
"related_apps": [
"libreoffice_calc"
],
"evaluator": {
"func": "infeasible",
"expected": {
},
"result": {
}
}
}

2
evaluation_examples/examples/libreoffice_impress/358aa0a7-6677-453f-ae35-e440f004c31e.json
View File

@@ -54,7 +54,7 @@
{
"type": "sleep",
"parameters": {
"seconds": 0.5
"seconds": 15
}
}
],

7
evaluation_examples/examples/libreoffice_impress/a669ef01-ded5-4099-9ea9-25e99b569840.json
View File

@@ -9,7 +9,7 @@
"parameters": {
"files": [
{
"url": "https://drive.usercontent.google.com/download?id=1C0u-Qvvwa6UbJVTzzQHfdNIgp2i051xA&export=download&authuser=0&confirm=t&uuid=5551a43c-3ff7-424f-b82c-50a5c96b5809&at=APZUnTViShb8pJUviOkmVtn7Pums:1707299959829",
"url": "https://drive.usercontent.google.com/download?id=1hr2flq5iSyMYSps6Jd-3pDOEfZoHFCbb&export=download&authuser=0&confirm=t&uuid=02746987-6ea8-4fbb-8817-8051dab152e7&at=APZUnTWaH071WARB_12CQDvjfg6b:1707314868059",
"path": "/home/user/Desktop/Writing-Outlines.pptx"
}
]
@@ -71,16 +71,13 @@
"func": "compare_pptx_files",
"expected": {
"type": "cloud_file",
"path": "https://drive.usercontent.google.com/download?id=1d4WJwm7KDhDIOJ9r9vKhRTrt_bF3PSln&export=download&authuser=0&confirm=t&uuid=a8ec87de-96cf-49f0-98e4-faa1218354fe&at=APZUnTWiOoiHFjyM4jTunLP4t5wE:1707299961717",
"path": "https://drive.usercontent.google.com/download?id=15mnwwGTDlelIf27C1HdJOiMgfEWNIoLl&export=download&authuser=0&confirm=t&uuid=b53e5fbb-565b-4498-9dc5-071eded307e0&at=APZUnTUdfXCDVFEQPCTYckB-H2Fn:1707314644205",
"dest": "Writing-Outlines_Gold.pptx"
},
"result": {
"type": "vm_file",
"path": "/home/user/Desktop/Writing-Outlines.pptx",
"dest": "Writing-Outlines.pptx"
},
"options": {
"examine_shape": false
}
}
}

2
evaluation_examples/examples/os/b3d4a89c-53f2-4d6b-8b6a-541fb5d205fa.json
View File

@@ -9,7 +9,7 @@
"os"
],
"evaluator": {
"func": "",
"func": "infeasible",
"result": {
},
"expected": {

2
evaluation_examples/examples/os/e2eb4bf1-aa93-4192-b55d-03e2fb6dfd15.json
View File

@@ -8,7 +8,7 @@
"os"
],
"evaluator": {
"func": "",
"func": "infeasible",
"result": {
},
"expected": {

19
evaluation_examples/examples/os/fe41f596-a71b-4c2f-9b2f-9dcd40b568c3.json
View File

@@ -5,32 +5,15 @@
"source": "https://help.ubuntu.com/lts/ubuntu-help/power-percentage.html.en",
"trajectory": "trajectories/",
"config": [
{
"type": "execute",
"parameters": {
"command": [
"python",
"-c",
"import pyautogui; import time; pyautogui.click(960, 540); time.sleep(0.5);"
]
}
}
],
"related_apps": [
"os"
],
"evaluator": {
"func": "exact_match",
"func": "infeasible",
"result": {
"type": "vm_command_line",
"command": "gsettings get org.gnome.desktop.interface show-battery-percentage",
"shell": true
},
"expected": {
"type": "rule",
"rules": {
"expected": "true\n"
}
}
}
}