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

122324154

Browse Source
This commit is contained in:
Timothyxxx
2024-02-02 14:36:53 +08:00
parent 32bcdd0937
commit 068c6f5769
7 changed files with 436 additions and 146 deletions
Download Patch File Download Diff File Expand all files Collapse all files

131
experiment_a11y_tree.py
View File

@@ -242,18 +242,18 @@ if __name__ == '__main__':
# main("libreoffice_calc", example_id)
impress_list = [
# "5d901039-a89c-4bfb-967b-bf66f4df075e",
# "550ce7e7-747b-495f-b122-acdc4d0b8e54",
# "455d3c66-7dc6-4537-a39a-36d3e9119df7",
# "af23762e-2bfd-4a1d-aada-20fa8de9ce07",
# "c59742c0-4323-4b9d-8a02-723c251deaa0",
# "ef9d12bd-bcee-4ba0-a40e-918400f43ddf",
# "9ec204e4-f0a3-42f8-8458-b772a6797cab",
# "0f84bef9-9790-432e-92b7-eece357603fb",
# "ce88f674-ab7a-43da-9201-468d38539e4a",
# "3b27600c-3668-4abd-8f84-7bcdebbccbdb",
# "a097acff-6266-4291-9fbd-137af7ecd439",
# "bf4e9888-f10f-47af-8dba-76413038b73c",
"5d901039-a89c-4bfb-967b-bf66f4df075e",
"550ce7e7-747b-495f-b122-acdc4d0b8e54",
"455d3c66-7dc6-4537-a39a-36d3e9119df7",
"af23762e-2bfd-4a1d-aada-20fa8de9ce07",
"c59742c0-4323-4b9d-8a02-723c251deaa0",
"ef9d12bd-bcee-4ba0-a40e-918400f43ddf",
"9ec204e4-f0a3-42f8-8458-b772a6797cab",
"0f84bef9-9790-432e-92b7-eece357603fb",
"ce88f674-ab7a-43da-9201-468d38539e4a",
"3b27600c-3668-4abd-8f84-7bcdebbccbdb",
"a097acff-6266-4291-9fbd-137af7ecd439",
"bf4e9888-f10f-47af-8dba-76413038b73c",
"21760ecb-8f62-40d2-8d85-0cee5725cb72"
]
# for example_id in impress_list:
@@ -326,27 +326,106 @@ if __name__ == '__main__':
# logger.error("An error occurred while running the example: %s", e)
# continue
from tqdm import tqdm
# for example_id in tqdm(vlc_list):
# try:
# main("vlc", example_id, gpt4_model="gpt-3.5-turbo-16k")
# except Exception as e:
# print(f"An error occurred while running the example: {e}")
# continue
chrome_list = [
"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"
]
# for example_id in tqdm(chrome_list):
# try:
# main("chrome", example_id, gpt4_model="gpt-3.5-turbo-16k")
# except Exception as e:
# print(f"An error occurred while running the example: {e}")
# continue
vs_code_list = [
# "0ed39f63-6049-43d4-ba4d-5fa2fe04a951",
# "53ad5833-3455-407b-bbc6-45b4c79ab8fb",
# "eabc805a-bfcf-4460-b250-ac92135819f6",
# "982d12a5-beab-424f-8d38-d2a48429e511",
# "4e60007a-f5be-4bfc-9723-c39affa0a6d3",
# "e2b5e914-ffe1-44d2-8e92-58f8c5d92bb2",
# "9439a27b-18ae-42d8-9778-5f68f891805e",
# "ea98c5d7-3cf9-4f9b-8ad3-366b58e0fcae",
# "930fdb3b-11a8-46fe-9bac-577332e2640e",
# "276cc624-87ea-4f08-ab93-f770e3790175",
# "9d425400-e9b2-4424-9a4b-d4c7abac4140"
]
for example_id in tqdm(vs_code_list):
try:
main("vs_code", example_id, gpt4_model="gpt-3.5-turbo-16k")
except Exception as e:
print(f"An error occurred while running the example: {e}")
continue
thunderbird_list = [
# "bb5e4c0d-f964-439c-97b6-bdb9747de3f4",
# "7b6c7e24-c58a-49fc-a5bb-d57b80e5b4c3",
"12086550-11c0-466b-b367-1d9e75b3910e",
"06fe7178-4491-4589-810f-2e2bc9502122",
"6766f2b8-8a72-417f-a9e5-56fcaa735837",
"e1e75309-3ddb-4d09-92ec-de869c928143",
"3d1682a7-0fb0-49ae-a4dc-a73afd2d06d5",
"35253b65-1c19-4304-8aa4-6884b8218fc0",
"d088f539-cab4-4f9a-ac92-9999fc3a656e",
"2ad9387a-65d8-4e33-ad5b-7580065a27ca",
"480bcfea-d68f-4aaa-a0a9-2589ef319381",
"030eeff7-b492-4218-b312-701ec99ee0cc",
"94760984-3ff5-41ee-8347-cf1af709fea0",
"99146c54-4f37-4ab8-9327-5f3291665e1e",
"c9e7eaf2-b1a1-4efc-a982-721972fa9f02"
]
# for example_id in tqdm(thunderbird_list):
# try:
# main("thunderbird", example_id, gpt4_model="gpt-3.5-turbo-16k")
# except Exception as e:
# print(f"An error occurred while running the example: {e}")
# continue
multiple_list = [
"f8cfa149-d1c1-4215-8dac-4a0932bad3c2",
"897e3b53-5d4d-444b-85cb-2cdc8a97d903",
"4e9f0faf-2ecc-4ae8-a804-28c9a75d1ddc",
"b52b40a5-ad70-4c53-b5b0-5650a8387052",
"46407397-a7d5-4c6b-92c6-dbe038b1457b",
"2b9493d7-49b8-493a-a71b-56cd1f4d6908",
"51f5801c-18b3-4f25-b0c3-02f85507a078",
"2c9fc0de-3ee7-45e1-a5df-c86206ad78b5",
"510f64c8-9bcc-4be1-8d30-638705850618",
"937087b6-f668-4ba6-9110-60682ee33441",
"ee9a3c83-f437-4879-8918-be5efbb9fac7",
# "f8cfa149-d1c1-4215-8dac-4a0932bad3c2",
# "897e3b53-5d4d-444b-85cb-2cdc8a97d903",
"2fe4b718-3bd7-46ec-bdce-b184f5653624",
"3680a5ee-6870-426a-a997-eba929a0d25c",
"e135df7c-7687-4ac0-a5f0-76b74438b53e",
# "4e9f0faf-2ecc-4ae8-a804-28c9a75d1ddc",
# "b52b40a5-ad70-4c53-b5b0-5650a8387052",
# "46407397-a7d5-4c6b-92c6-dbe038b1457b",
# "2b9493d7-49b8-493a-a71b-56cd1f4d6908",
# "51f5801c-18b3-4f25-b0c3-02f85507a078",
"58565672-7bfe-48ab-b828-db349231de6b",
"2fe4b718-3bd7-46ec-bdce-b184f5653624"
# "2c9fc0de-3ee7-45e1-a5df-c86206ad78b5",
# "510f64c8-9bcc-4be1-8d30-638705850618",
# "937087b6-f668-4ba6-9110-60682ee33441",
# "ee9a3c83-f437-4879-8918-be5efbb9fac7",
# "3680a5ee-6870-426a-a997-eba929a0d25c",
# "e135df7c-7687-4ac0-a5f0-76b74438b53e",
"ee9a3c83-f437-4879-8918-be5efbb9fac7",
# "58565672-7bfe-48ab-b828-db349231de6b",
# "2fe4b718-3bd7-46ec-bdce-b184f5653624"
]
for example_id in multiple_list:
try:
main("multi_apps", example_id)
main("multi_apps", example_id, gpt4_model="gpt-3.5-turbo-16k")
except Exception as e:
logger.error("An error occurred while running the example: %s", e)
continue