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

ver Feb26thv2

Browse Source 
updated two new chrome tasks
This commit is contained in:
David Chang
2024-02-26 23:19:17 +08:00
parent 2a1477996d
commit 1ed763591b
2 changed files with 7 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
evaluation_examples/examples/chrome/82bc8d6a-36eb-4d2d-8801-ef714fb1e55a.json
View File

@@ -1,7 +1,7 @@
{
"id": "82bc8d6a-36eb-4d2d-8801-ef714fb1e55a",
"snapshot": "chrome",
"instruction": "On April 21, look up a flight from Mumbai to Stockholm.",
"instruction": "On next Monday, look up a flight from Mumbai to Stockholm.",
"source": "test_task_1",
"config": [
{
@@ -61,10 +61,9 @@
"expected": {
"fromStation": "BOM",
"toStation": "STO",
"time": "{Year}-{Month0D}-{DayD}"
"time": "{Year}-{Month0D}-{Day0D}"
}
}
}
}
}
}

9
evaluation_examples/examples/chrome/da46d875-6b82-4681-9284-653b0c7ae241.json
View File

@@ -1,7 +1,7 @@
{
"id": "da46d875-6b82-4681-9284-653b0c7ae241",
"snapshot": "chrome",
"instruction": "Schedule an appointment to apply for transportation access pass in the Charlie Card store on the first Monday four months later, 10:15 am, fill in my details (James Smith, james.smith@gmail.com), and book.",
"instruction": "Schedule an appointment to apply for transportation access pass in the Charlie Card store on the first Monday four months later, 10:15 am, fill in my details (James Smith, james.smith@gmail.com). And don not click \"book\" directly. Let me review it.",
"source": "test_task_2",
"config": [
{
@@ -58,7 +58,7 @@
"1": "content",
"2": "time"
}
}
}
},
{
"type": "active_tab_html_parse",
@@ -74,7 +74,7 @@
"type": "rule",
"rules":{
"expected": ["CharlieCardStoreAppointments@mbta.com\/bookings\/"]
}
}
},
{
"type": "rule_relativeTime",
@@ -99,5 +99,4 @@
}
]
}
}
}