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

fix some multi_apps tasks (#245)

Browse Source 
* fix chrome

* fix some multi_apps tasks.

* fix some multiapps tasks

* fix some multiapps tasks

---------

Co-authored-by: yuanmengqi <yuanmengqi@mail.ustc.edu.cn>
This commit is contained in:
st2rb8g
2025-07-11 06:32:13 +08:00
committed by GitHub
parent 4e3446d6fe
commit 61f265a082
8 changed files with 42 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
evaluation_examples/examples/multi_apps/ce2b64a2-ddc1-4f91-8c7d-a88be7121aac.json
View File

@@ -1,7 +1,7 @@
{
"id": "ce2b64a2-ddc1-4f91-8c7d-a88be7121aac",
"snapshot": "multiapps",
"instruction": "There are several pictures of mountains in my Pictures directory, but I don’t know the names of these mountains. Please help me identify these pictures and change the names of these pictures to the names of the mountains in the pictures.",
"instruction": "There are several pictures of mountains in my Pictures directory, but I don’t know the names of these mountains. Please help me identify these pictures and change the names of these pictures to the names of the mountains in the pictures (You don't need to add \"Mount\" before the name of the mountain).",
"source": "authors",
"config": [
{
@@ -69,19 +69,20 @@
"rules": {
"expected": {
"ec076282f61ba74642e94b5a6a1250c6988204d59d9b02936606b6b8ef1e4433": [
"Kilimanjaro"
"Kilimanjaro.jpg"
],
"6ed4239ecc2be3ec15ad65a78c5c823b9004d640b8cc83a6a7af5930f354de91": [
"Himalayas",
"Everest",
"Sagarmatha"
"Himalayas.jpg",
"Everest.jpg",
"Sagarmatha.jpg"
],
"79f45d40d8413d4e81f1b9734ea39e58622cafd79e12bab32959643fc245147c": [
"Hua",
"hua"
"Hua.jpg",
"hua.jpg"
]
},
"expect_in_result": true
"expect_in_result": true,
"result_not_list": true
}
}
},

2
evaluation_examples/examples/multi_apps/da922383-bfa4-4cd3-bbad-6bebab3d7742.json
View File

@@ -1,7 +1,7 @@
{
"id": "da922383-bfa4-4cd3-bbad-6bebab3d7742",
"snapshot": "multiapps",
"instruction": "I browsed a lot of interesting blog articles today. I hope to store these articles in my local designated folder just like zotero stores papers. Please download the blogs opening now in pdf format and save them in their tile to /home/user/Documents/Blog.",
"instruction": "I browsed a lot of interesting blog articles today. I hope to store these articles in my local designated folder just like zotero stores papers. Please download the blogs opening now in pdf format and save them in their title to /home/user/Documents/Blog.",
"source": "authors",
"config": [
{

7
evaluation_examples/examples/multi_apps/e135df7c-7687-4ac0-a5f0-76b74438b53e.json
View File

@@ -89,7 +89,14 @@
"path": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/e135df7c-7687-4ac0-a5f0-76b74438b53e/annual-enterprise-survey-2021-financial-year-provisional.html",
"dest": "annual-enterprise-survey-2021-financial-year-provisional_gold.html"
}
],
"options": [
{},
{
"ignore_sdnum": true
}
]
},
"proxy": true
}

4
evaluation_examples/examples/multi_apps/e8172110-ec08-421b-a6f5-842e6451911f.json
View File

@@ -36,8 +36,8 @@
],
"evaluator": {
"func": [
"check_structure_sim",
"check_structure_sim"
"check_structure_sim_resized",
"check_structure_sim_resized"
],
"result": [
{

6
evaluation_examples/examples/multi_apps/f8cfa149-d1c1-4215-8dac-4a0932bad3c2.json
View File

@@ -10,7 +10,7 @@
"files": [
{
"url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/f8cfa149-d1c1-4215-8dac-4a0932bad3c2/file.xls",
"path": "/home/user/cell_search.xlsx"
"path": "/home/user/cell_search.xls"
}
]
}
@@ -47,7 +47,7 @@
{
"type": "open",
"parameters": {
"path": "/home/user/cell_search.xlsx"
"path": "/home/user/cell_search.xls"
}
}
],
@@ -65,7 +65,7 @@
"type": "rule",
"rules": {
"expect": {
"pattern": "www\\.google\\.com.*?/search\\?q=Nereida&"
"pattern": "https?://(www\\.?)?google\\.com/search\\?q=nereida(&|$)"
}
}
}