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

Final review multi_apps fix Xinzhuang part

Browse Source
This commit is contained in:
yuanmengqi
2025-07-12 16:34:55 +00:00
parent 6f0382c0c2
commit 877e75a013
5 changed files with 187 additions and 34 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
}