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

Merge branch 'main' into fix_chrome

Browse Source
This commit is contained in:
yuanmengqi
2025-07-13 10:16:08 +00:00
parent a16b54c175
commit 572a94b6df
15 changed files with 228 additions and 128 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
evaluation_examples/examples/multi_apps/2373b66a-092d-44cb-bfd7-82e86e7a3b4d.json
View File

@@ -1,7 +1,7 @@
{
"id": "2373b66a-092d-44cb-bfd7-82e86e7a3b4d",
"snapshot": "multiapps",
"instruction": "I want to understand the resource usage of my Ubuntu system under normal workloads. Please use the `sar` command in the `sysstat` toolkit to monitor system activity, evaluate the status once every second for 30 seconds, output the results to \"System_Resources_Report.txt\" under Desktop.",
"instruction": "Monitor Ubuntu system resource usage using the sar command from sysstat toolkit. Collect CPU statistics every second for 30 seconds and save the output to 'System_Resources_Report.txt' on Desktop.",
"source": "author",
"config": [
{

15
evaluation_examples/examples/multi_apps/3680a5ee-6870-426a-a997-eba929a0d25c.json
View File

@@ -37,6 +37,7 @@
"check_include_exclude",
"compare_csv"
],
"conj": "and",
"result": [
{
"type": "vm_command_line",
@@ -63,8 +64,18 @@
},
{
"type": "cloud_file",
"path": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/3680a5ee-6870-426a-a997-eba929a0d25c/output.csv",
"dest": "output_gold.csv"
"multi": true,
"path": [
"https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/3680a5ee-6870-426a-a997-eba929a0d25c/output.csv",
"https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/3680a5ee-6870-426a-a997-eba929a0d25c/output_gold2.csv",
"https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/3680a5ee-6870-426a-a997-eba929a0d25c/output_gold3.csv"
],
"dest": [
"output_gold.csv",
"output_gold2.csv",
"output_gold3.csv"
],
"gives": [0, 1, 2]
}
]
},

51
evaluation_examples/examples/multi_apps/42d25c08-fb87-4927-8b65-93631280a26f.json
View File

@@ -144,17 +144,46 @@
"os"
],
"evaluator": {
"func": "compare_epub",
"result": {
"type": "vm_file",
"dest": "Pass Through.epub",
"path": "/home/user/Documents/Novels/Pass Through/Pass Through.epub"
},
"expected": {
"type": "cloud_file",
"path": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/42d25c08-fb87-4927-8b65-93631280a26f/Pass%20Through.epub",
"dest": "Pass Through Gold.epub"
}
"func": [
"compare_epub",
"compare_epub",
"compare_epub"
],
"conj": "or",
"result": [
{
"type": "vm_file",
"dest": "Pass Through.epub",
"path": "/home/user/Documents/Novels/Pass Through/Pass Through.epub"
},
{
"type": "vm_file",
"dest": "Pass Through.epub",
"path": "/home/user/Documents/Novels/Pass Through/Pass_Through.epub"
},
{
"type": "vm_file",
"dest": "Pass Through.epub",
"path": "/home/user/Documents/Novels/Pass Through/pass_through.epub"
}
],
"expected": [
{
"type": "cloud_file",
"path": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/42d25c08-fb87-4927-8b65-93631280a26f/Pass%20Through.epub",
"dest": "Pass Through Gold.epub"
},
{
"type": "cloud_file",
"path": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/42d25c08-fb87-4927-8b65-93631280a26f/Pass%20Through.epub",
"dest": "Pass Through Gold.epub"
},
{
"type": "cloud_file",
"path": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/42d25c08-fb87-4927-8b65-93631280a26f/Pass%20Through.epub",
"dest": "Pass Through Gold.epub"
}
]
},
"proxy": true
}

14
evaluation_examples/examples/multi_apps/a82b78bb-7fde-4cb3-94a4-035baf10bcf0.json
View File

@@ -83,21 +83,27 @@
"urls": [
[
"https://jimfan.me/",
"https://research.nvidia.com/person/linxi-jim-fan"
"https://research.nvidia.com/person/linxi-jim-fan",
"https://www.linkedin.com/in/drjimfan/"
],
[
"https://research.nvidia.com/person/de-an-huang",
"https://ai.stanford.edu/~dahuang/"
"https://ai.stanford.edu/~dahuang/",
"https://www.linkedin.com/in/de-an-huang-38242a69"
],
[
"https://yukezhu.me/",
"https://www.cs.utexas.edu/people/faculty-researchers/yuke-zhu",
"https://experts.utexas.edu/yuke_zhu",
"https://research.nvidia.com/person/yuke-zhu"
"https://research.nvidia.com/person/yuke-zhu",
"https://www.linkedin.com/in/yukez/"
],
[
"https://tensorlab.cms.caltech.edu/users/anima/",
"http://tensorlab.cms.caltech.edu/users/anima/",
"https://www.eas.caltech.edu/people/anima"
"https://www.eas.caltech.edu/people/anima",
"https://en.wikipedia.org/wiki/Anima_Anandkumar",
"https://www.linkedin.com/in/anima-anandkumar/"
]
]
}

16
evaluation_examples/examples/multi_apps/e8172110-ec08-421b-a6f5-842e6451911f.json
View File

@@ -11,10 +11,6 @@
{
"url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/e8172110-ec08-421b-a6f5-842e6451911f/character.png",
"path": "/home/user/Desktop/character.png"
},
{
"url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/e8172110-ec08-421b-a6f5-842e6451911f/character_no_background_gold.png",
"path": "/home/user/Desktop/character_no_background_gold.png"
}
]
}
@@ -36,8 +32,8 @@
],
"evaluator": {
"func": [
"check_structure_sim_resized",
"check_structure_sim_resized"
"check_structure_sim",
"check_structure_sim"
],
"result": [
{
@@ -53,13 +49,13 @@
],
"expected": [
{
"type": "vm_file",
"path": "/home/user/Desktop/character_no_background_gold.png",
"type": "cloud_file",
"path": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/e8172110-ec08-421b-a6f5-842e6451911f/character_no_background_gold.png",
"dest": "character_no_background_gold.png"
},
{
"type": "vm_file",
"path": "/home/user/Desktop/character_no_background_gold.png",
"type": "cloud_file",
"path": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/e8172110-ec08-421b-a6f5-842e6451911f/character_no_background_gold.png",
"dest": "character_no_background_gold.png"
}
]

2
evaluation_examples/examples/multi_apps/f8cfa149-d1c1-4215-8dac-4a0932bad3c2.json
View File

@@ -65,7 +65,7 @@
"type": "rule",
"rules": {
"expect": {
"pattern": "https?://(www\\.?)?google\\.com/search\\?q=nereida(&|$)"
"pattern": "(?i)https?://(?:www\\.)?google\\.com/search\\?q=nereida(?:&|$|#).*"
}
}
}