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

update multi apps

Browse Source
This commit is contained in:
tsuky_chen
2024-03-07 17:20:51 +08:00
parent e295430bcf
commit 807a95a230
20 changed files with 104 additions and 63 deletions
Download Patch File Download Diff File Expand all files Collapse all files

30
evaluation_examples/examples/multi_apps/869de13e-bef9-4b91-ba51-f6708c40b096.json
View File

@@ -1,7 +1,7 @@
{
"id": "869de13e-bef9-4b91-ba51-f6708c40b096",
"snapshot": "libreoffice_calc",
"instruction": "Can you organize my desktop by identifying schoolwork-related files, coding projects, and random downloads, ensuring no file is misplaced? Specifically, schoolwork files should end up in the 'Work' folder, coding projects in 'Projects', and everything else in 'Miscellaneous'. Use content analysis for files without clear extensions or names.",
"instruction": "Can you organize my desktop by identifying academic papers, coding projects, and other documents, ensuring no file is misplaced? Specifically, place academic papers in the 'Paper_reading' folder, coding projects in 'Projects,' and categorize everything else under 'Miscellaneous.' For files lacking clear extensions or names, apply content analysis to determine their appropriate classification.",
"source": "authors",
"config": [
{
@@ -10,7 +10,7 @@
"command": [
"mkdir",
"-p",
"/home/user/Desktop/Work"
"/home/user/Desktop/Paper_reading"
]
}
},
@@ -77,6 +77,26 @@
{
"url": "https://drive.usercontent.google.com/download?id=1O1yd3Dm_nKEtknQYzDAHqPllv0BeQ2bp&export=download&authuser=0&confirm=t&uuid=636ee37e-4ee1-4415-ba71-73e42335c4bf&at=APZUnTW7tJhD6LG7CglaqI_y0Exu:1709357564381",
"path": "/home/user/Desktop/S1578219008703378.pdf"
},
{
"url": "https://drive.usercontent.google.com/download?id=1WA-QneFJF9JJ_KKs9ksZ8N7ggkhRIt6Y&export=download&authuser=0&confirm=t&uuid=3fbc694a-8470-4a8f-a6e9-9d64d94b3a5e&at=APZUnTXi4PtZ42zRYDj-VGbqH2Ts:1709793215203",
"path": "/home/user/Desktop/paper01.pdf"
},
{
"url": "https://drive.usercontent.google.com/download?id=1FbSBvFQCq5prYdxLimy6Lp9xfe1qwERn&export=download&authuser=0&confirm=t&uuid=7b217188-be64-4f44-8cda-5481de3b0886&at=APZUnTWQCZ0FiYLqOyv4zyVOJFwR:1709793258104",
"path": "/home/user/Desktop/GLUE: A MULTI-TASK BENCHMARK AND ANALYSIS.pdf"
},
{
"url": "https://drive.usercontent.google.com/download?id=1YQEqiEQUOhaYjcff4xxypoXcMpUZHobI&export=download&authuser=0&confirm=t&uuid=86d82134-d017-43af-9b72-808fa63c3cc6&at=APZUnTUUlrZzFH4zE9doTOp8MzoE:1709793311945",
"path": "/home/user/Desktop/1909.10351.pdf"
},
{
"url": "https://drive.usercontent.google.com/download?id=11XxrawBkBJqU-DHf6Nn2v8lo3PDIQeFA&export=download&authuser=0&confirm=t&uuid=f6f871eb-6d71-465b-bda0-8a930042901c&at=APZUnTXFrrX-QEcVCuY76F7b2rQz:1709793354326",
"path": "/home/user/Desktop/1802.05365.pdf"
},
{
"url": "https://drive.usercontent.google.com/download?id=1wBXTSelPU4-uuH-Vm9Cw1CrtAxfNq9M7&export=download&authuser=0&confirm=t&uuid=bac4cbc0-aad2-4496-bfb4-921f1c7522f3&at=APZUnTWnVERriP_pBtYBT-ECQZg0:1709793392844",
"path": "/home/user/Desktop/1706.03762.pdf"
}
]
}
@@ -110,7 +130,7 @@
"type": "vm_command_line",
"command": [
"ls",
"/home/user/Desktop/Work"
"/home/user/Desktop/Paper_reading"
]
},
{
@@ -132,7 +152,7 @@
{
"type": "rule",
"rules": {
"expected": "07-cluster-kMean (1).ppt\nassignment_mark_frontpage.docx\ncco-return-to-school-survey-underlying-data-tables.xlsx\nDOC_2480903712718068684.pdf\nIA_Format.docx\n"
"expected": "1706.03762.pdf\n1802.05365.pdf\n1909.10351.pdf\nGLUE: A MULTI-TASK BENCHMARK AND ANALYSIS.pdf\npaper01.pdf\n"
}
},
{
@@ -144,7 +164,7 @@
{
"type": "rule",
"rules": {
"expected": "2023_validation_7bd855d8-463d-4ed5-93ca-5fe35145f733.xlsx\nFamily Status Equality-Eng (Aug 2021).pdf\nS1578219008703378.pdf\n"
"expected": "07-cluster-kMean (1).ppt\n2023_validation_7bd855d8-463d-4ed5-93ca-5fe35145f733.xlsx\nassignment_mark_frontpage.docx\ncco-return-to-school-survey-underlying-data-tables.xlsx\nDOC_2480903712718068684.pdf\nFamily Status Equality-Eng (Aug 2021).pdf\nIA_Format.docx\nS1578219008703378.pdf\n"
}
}
]