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(&|$)"
"pattern": "(?i)https?://(?:www\\.)?google\\.com/search\\?q=nereida(?:&|$|#).*"
}
}
}

50
evaluation_examples/test_fix_chrome.json
View File

@@ -1,50 +0,0 @@
{
"chrome": [
"bb5e4c0d-f964-439c-97b6-bdb9747de3f4",
"7b6c7e24-c58a-49fc-a5bb-d57b80e5b4c3",
"06fe7178-4491-4589-810f-2e2bc9502122",
"e1e75309-3ddb-4d09-92ec-de869c928143",
"35253b65-1c19-4304-8aa4-6884b8218fc0",
"2ad9387a-65d8-4e33-ad5b-7580065a27ca",
"7a5a7856-f1b6-42a4-ade9-1ca81ca0f263",
"44ee5668-ecd5-4366-a6ce-c1c9b8d4e938",
"2ae9ba84-3a0d-4d4c-8338-3a1478dc5fe3",
"480bcfea-d68f-4aaa-a0a9-2589ef319381",
"af630914-714e-4a24-a7bb-f9af687d3b91",
"3720f614-37fd-4d04-8a6b-76f54f8c222d",
"99146c54-4f37-4ab8-9327-5f3291665e1e",
"12086550-11c0-466b-b367-1d9e75b3910e",
"6766f2b8-8a72-417f-a9e5-56fcaa735837",
"93eabf48-6a27-4cb6-b963-7d5fe1e0d3a9",
"ae78f875-5b98-4907-bbb5-9c737fc68c03",
"3299584d-8f11-4457-bf4c-ce98f7600250",
"030eeff7-b492-4218-b312-701ec99ee0cc",
"9656a811-9b5b-4ddf-99c7-5117bcef0626",
"fc6d8143-9452-4171-9459-7f515143419a",
"a96b564e-dbe9-42c3-9ccf-b4498073438a",
"1704f00f-79e6-43a7-961b-cedd3724d5fd",
"f3b19d1e-2d48-44e9-b4e1-defcae1a0197",
"82bc8d6a-36eb-4d2d-8801-ef714fb1e55a",
"47543840-672a-467d-80df-8f7c3b9788c9",
"c1fa57f3-c3db-4596-8f09-020701085416",
"da46d875-6b82-4681-9284-653b0c7ae241",
"6c4c23a1-42a4-43cc-9db1-2f86ff3738cc",
"f79439ad-3ee8-4f99-a518-0eb60e5652b0",
"b7895e80-f4d1-4648-bee0-4eb45a6f1fa8",
"9f3f70fc-5afc-4958-a7b7-3bb4fcb01805",
"7f52cab9-535c-4835-ac8c-391ee64dc930",
"82279c77-8fc6-46f6-9622-3ba96f61b477",
"2888b4e6-5b47-4b57-8bf5-c73827890774",
"b4f95342-463e-4179-8c3f-193cd7241fb2",
"f5d96daf-83a8-4c86-9686-bada31fc66ab",
"121ba48f-9e17-48ce-9bc6-a4fb17a7ebba",
"368d9ba4-203c-40c1-9fa3-da2f1430ce63",
"59155008-fe71-45ec-8a8f-dc35497b6aa8",
"a728a36e-8bf1-4bb6-9a03-ef039a5233f0",
"b070486d-e161-459b-aa2b-ef442d973b92",
"0d8b7de3-e8de-4d86-b9fd-dd2dce58a217",
"9f935cce-0a9f-435f-8007-817732bfc0a5",
"f0b971a1-6831-4b9b-a50e-22a6e47f45ba",
"cabb3bae-cccb-41bd-9f5d-0f3a9fecd825"
]
}