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

Improve on mmagents prompts; initialize online tasks from Mind2Web

Browse Source
This commit is contained in:
Timothyxxx
2024-02-22 22:01:22 +08:00
parent 938a3bb918
commit 030574e316
17 changed files with 293 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
evaluation_examples/examples/chrome/0d8b7de3-e8de-4d86-b9fd-dd2dce58a217.json Normal file
View File

@@ -0,0 +1,18 @@
{
"id": "0d8b7de3-e8de-4d86-b9fd-dd2dce58a217",
"snapshot": "chrome",
"instruction": "Browse the natural products database.",
"source": "Mind2Web",
"config": [],
"trajectory": "trajectories/",
"related_apps": [
"chrome"
],
"evaluator": {
"func": "",
"result": {
},
"expected": {
}
}
}

18
evaluation_examples/examples/chrome/121ba48f-9e17-48ce-9bc6-a4fb17a7ebba.json Normal file
View File

@@ -0,0 +1,18 @@
{
"id": "121ba48f-9e17-48ce-9bc6-a4fb17a7ebba",
"snapshot": "chrome",
"instruction": "Find Dota 2 game and add all DLC to cart.",
"source": "Mind2Web",
"config": [],
"trajectory": "trajectories/",
"related_apps": [
"chrome"
],
"evaluator": {
"func": "",
"result": {
},
"expected": {
}
}
}

18
evaluation_examples/examples/chrome/1236ab8d-ad0c-4643-bdf1-9712a35e7e47.json Normal file
View File

@@ -0,0 +1,18 @@
{
"id": "1236ab8d-ad0c-4643-bdf1-9712a35e7e47",
"snapshot": "chrome",
"instruction": "Show me jobs for MBA & Graduate Internships.",
"source": "Mind2Web",
"config": [],
"trajectory": "trajectories/",
"related_apps": [
"chrome"
],
"evaluator": {
"func": "",
"result": {
},
"expected": {
}
}
}

18
evaluation_examples/examples/chrome/368d9ba4-203c-40c1-9fa3-da2f1430ce63.json Normal file
View File

@@ -0,0 +1,18 @@
{
"id": "368d9ba4-203c-40c1-9fa3-da2f1430ce63",
"snapshot": "chrome",
"instruction": "find the Monthly forecast for Manchester, GB for January",
"source": "Mind2Web",
"config": [],
"trajectory": "trajectories/",
"related_apps": [
"chrome"
],
"evaluator": {
"func": "",
"result": {
},
"expected": {
}
}
}

18
evaluation_examples/examples/chrome/59155008-fe71-45ec-8a8f-dc35497b6aa8.json Normal file
View File

@@ -0,0 +1,18 @@
{
"id": "",
"snapshot": "chrome",
"instruction": "",
"source": "Mind2Web",
"config": [],
"trajectory": "trajectories/",
"related_apps": [
"chrome"
],
"evaluator": {
"func": "",
"result": {
},
"expected": {
}
}
}

18
evaluation_examples/examples/chrome/7f80d204-6db3-4cc2-8098-9b64302c02a1.json Normal file
View File

@@ -0,0 +1,18 @@
{
"id": "7f80d204-6db3-4cc2-8098-9b64302c02a1",
"snapshot": "chrome",
"instruction": "Check drug interaction for melatonin and Folate Forte.",
"source": "Mind2Web",
"config": [],
"trajectory": "trajectories/",
"related_apps": [
"chrome"
],
"evaluator": {
"func": "",
"result": {
},
"expected": {
}
}
}

18
evaluation_examples/examples/chrome/92615024-0cb5-409a-a61d-4932e22fdbf4.json Normal file
View File

@@ -0,0 +1,18 @@
{
"id": "92615024-0cb5-409a-a61d-4932e22fdbf4",
"snapshot": "chrome",
"instruction": "Find the drug interaction between gabapentin and ibuprofen",
"source": "Mind2Web",
"config": [],
"trajectory": "trajectories/",
"related_apps": [
"chrome"
],
"evaluator": {
"func": "",
"result": {
},
"expected": {
}
}
}

18
evaluation_examples/examples/chrome/96249224-cb8e-4504-a661-7e88f9efe347.json Normal file
View File

@@ -0,0 +1,18 @@
{
"id": "96249224-cb8e-4504-a661-7e88f9efe347",
"snapshot": "chrome",
"instruction": "View the speakers that are bluetooth and wireless and filter the results to only show models that are on sale and cost less than $200.",
"source": "Mind2Web",
"config": [],
"trajectory": "trajectories/",
"related_apps": [
"chrome"
],
"evaluator": {
"func": "",
"result": {
},
"expected": {
}
}
}

18
evaluation_examples/examples/chrome/99a48441-ead6-4271-8c07-dc03e870f507.json Normal file
View File

@@ -0,0 +1,18 @@
{
"id": "99a48441-ead6-4271-8c07-dc03e870f507",
"snapshot": "chrome",
"instruction": "Look for a White PlayStation 5 Console and save it",
"source": "Mind2Web",
"config": [],
"trajectory": "trajectories/",
"related_apps": [
"chrome"
],
"evaluator": {
"func": "",
"result": {
},
"expected": {
}
}
}

18
evaluation_examples/examples/chrome/9f935cce-0a9f-435f-8007-817732bfc0a5.json Normal file
View File

@@ -0,0 +1,18 @@
{
"id": "9f935cce-0a9f-435f-8007-817732bfc0a5",
"snapshot": "chrome",
"instruction": "Browse list of Civil Division forms.",
"source": "Mind2Web",
"config": [],
"trajectory": "trajectories/",
"related_apps": [
"chrome"
],
"evaluator": {
"func": "",
"result": {
},
"expected": {
}
}
}

18
evaluation_examples/examples/chrome/a728a36e-8bf1-4bb6-9a03-ef039a5233f0.json Normal file
View File

@@ -0,0 +1,18 @@
{
"id": "a728a36e-8bf1-4bb6-9a03-ef039a5233f0",
"snapshot": "chrome",
"instruction": "Find the Driver License Eligibility Requirements",
"source": "Mind2Web",
"config": [],
"trajectory": "trajectories/",
"related_apps": [
"chrome"
],
"evaluator": {
"func": "",
"result": {
},
"expected": {
}
}
}

18
evaluation_examples/examples/chrome/b070486d-e161-459b-aa2b-ef442d973b92.json Normal file
View File

@@ -0,0 +1,18 @@
{
"id": "b070486d-e161-459b-aa2b-ef442d973b92",
"snapshot": "chrome",
"instruction": "Show side effects of Tamiflu.",
"source": "Mind2Web",
"config": [],
"trajectory": "trajectories/",
"related_apps": [
"chrome"
],
"evaluator": {
"func": "",
"result": {
},
"expected": {
}
}
}

18
evaluation_examples/examples/chrome/b538b896-8e4a-49b6-8d4a-188d5cc2c2ac.json Normal file
View File

@@ -0,0 +1,18 @@
{
"id": "b538b896-8e4a-49b6-8d4a-188d5cc2c2ac",
"snapshot": "chrome",
"instruction": "Find symptoms of sleep apnea",
"source": "Mind2Web",
"config": [],
"trajectory": "trajectories/",
"related_apps": [
"chrome"
],
"evaluator": {
"func": "",
"result": {
},
"expected": {
}
}
}

18
evaluation_examples/examples/chrome/cabb3bae-cccb-41bd-9f5d-0f3a9fecd825.json Normal file
View File

@@ -0,0 +1,18 @@
{
"id": "cabb3bae-cccb-41bd-9f5d-0f3a9fecd825",
"snapshot": "chrome",
"instruction": "Browse spider-man toys for kids and sort by lowest price.",
"source": "Mind2Web",
"config": [],
"trajectory": "trajectories/",
"related_apps": [
"chrome"
],
"evaluator": {
"func": "",
"result": {
},
"expected": {
}
}
}

18
evaluation_examples/examples/chrome/f0b971a1-6831-4b9b-a50e-22a6e47f45ba.json Normal file
View File

@@ -0,0 +1,18 @@
{
"id": "f0b971a1-6831-4b9b-a50e-22a6e47f45ba",
"snapshot": "chrome",
"instruction": "Show me the scores for the 2019 super bowl",
"source": "Mind2Web",
"config": [],
"trajectory": "trajectories/",
"related_apps": [
"chrome"
],
"evaluator": {
"func": "",
"result": {
},
"expected": {
}
}
}

18
evaluation_examples/examples/chrome/f5d96daf-83a8-4c86-9686-bada31fc66ab.json Normal file
View File

@@ -0,0 +1,18 @@
{
"id": "f5d96daf-83a8-4c86-9686-bada31fc66ab",
"snapshot": "chrome",
"instruction": "Compare iPhone 15 Pro Max with iPhone 13 Pro Max",
"source": "Mind2Web",
"config": [],
"trajectory": "trajectories/",
"related_apps": [
"chrome"
],
"evaluator": {
"func": "",
"result": {
},
"expected": {
}
}
}