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

feat: Migrate OSWorld files to HuggingFace cache with comprehensive documentation

Browse Source 
- Add detailed README for file cache repository
- Implement migration script with retry logic and browser simulation
- Support automatic file type detection and deduplication
- Ensure reliable hosting for OSWorld evaluation files
This commit is contained in:
Timothyxxx
2025-05-28 04:29:37 +08:00
parent a845824f06
commit 34748567a5
317 changed files with 12630 additions and 12008 deletions
Download Patch File Download Diff File Expand all files Collapse all files

167
evaluation_examples/examples/multi_apps/aceb0368-56b8-4073-b70e-3dc9aee184e0.json
View File

@@ -1,87 +1,86 @@
{
"id": "aceb0368-56b8-4073-b70e-3dc9aee184e0",
"snapshot": "libreoffice_calc",
"instruction": "I am grading students' English exam papers, but the test consists only of multiple-choice questions. It's too exhausting to check each question one by one and record the detailed scores. Can you help me compare the remaining students' answers with the answer key and record the detailed scoring in the opened spreadsheet?",
"source": "authors",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://drive.usercontent.google.com/download?id=1CfzBZxhhV1_vUKhxsP_4M574-XFm1qIo&export=download&authuser=0&confirm=t",
"path": "/home/user/exam.zip"
}
]
}
},
{
"type": "execute",
"parameters": {
"command": [
"unzip",
"/home/user/exam.zip",
"-d",
"/home/user/"
]
}
},
{
"type": "launch",
"parameters": {
"command": [
"libreoffice",
"--writer",
"/home/user/exam/ReferenceAnswers.docx"
]
}
},
{
"type": "launch",
"parameters": {
"command": [
"libreoffice",
"--calc",
"/home/user/exam/grades.xlsx"
]
}
},
{
"type": "launch",
"parameters": {
"command": [
"nautilus",
"/home/user/exam/"
]
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"thunderbird",
"os"
],
"evaluator": {
"func": "compare_table",
"expected": {
"type": "cloud_file",
"path": "https://drive.google.com/uc?id=1a0gZwixcJuZAUtqGR3L5P20JmoWfQU_d&export=download&authuser=0&confirm=t",
"dest": "gold_grades.xlsx"
},
"result": {
"type": "vm_file",
"path": "/home/user/exam/grades.xlsx",
"dest": "grades.xlsx"
},
"options": {
"rules": [
{
"type": "sheet_data",
"sheet_idx0": 0,
"sheet_idx1": "EI0"
}
]
}
"id": "aceb0368-56b8-4073-b70e-3dc9aee184e0",
"snapshot": "libreoffice_calc",
"instruction": "I am grading students' English exam papers, but the test consists only of multiple-choice questions. It's too exhausting to check each question one by one and record the detailed scores. Can you help me compare the remaining students' answers with the answer key and record the detailed scoring in the opened spreadsheet?",
"source": "authors",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/aceb0368-56b8-4073-b70e-3dc9aee184e0/exam.zip",
"path": "/home/user/exam.zip"
}
]
}
},
{
"type": "execute",
"parameters": {
"command": [
"unzip",
"/home/user/exam.zip",
"-d",
"/home/user/"
]
}
},
{
"type": "launch",
"parameters": {
"command": [
"libreoffice",
"--writer",
"/home/user/exam/ReferenceAnswers.docx"
]
}
},
{
"type": "launch",
"parameters": {
"command": [
"libreoffice",
"--calc",
"/home/user/exam/grades.xlsx"
]
}
},
{
"type": "launch",
"parameters": {
"command": [
"nautilus",
"/home/user/exam/"
]
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"thunderbird",
"os"
],
"evaluator": {
"func": "compare_table",
"expected": {
"type": "cloud_file",
"path": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/aceb0368-56b8-4073-b70e-3dc9aee184e0/grades.xlsx",
"dest": "gold_grades.xlsx"
},
"result": {
"type": "vm_file",
"path": "/home/user/exam/grades.xlsx",
"dest": "grades.xlsx"
},
"options": {
"rules": [
{
"type": "sheet_data",
"sheet_idx0": 0,
"sheet_idx1": "EI0"
}
]
}
}
}