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

5
evaluation_examples/examples/chrome/82bc8d6a-36eb-4d2d-8801-ef714fb1e55a.json
View File

@@ -1,7 +1,7 @@
{ {
"id": "82bc8d6a-36eb-4d2d-8801-ef714fb1e55a", "id": "82bc8d6a-36eb-4d2d-8801-ef714fb1e55a",
"snapshot": "chrome", "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", "source": "test_task_1",
"config": [ "config": [
{ {
@@ -61,10 +61,9 @@
"expected": { "expected": {
"fromStation": "BOM", "fromStation": "BOM",
"toStation": "STO", "toStation": "STO",
"time": "{Year}-{Month0D}-{DayD}" "time": "{Year}-{Month0D}-{Day0D}"
} }
} }
} }
} }
} }

3
evaluation_examples/examples/chrome/da46d875-6b82-4681-9284-653b0c7ae241.json
View File

@@ -1,7 +1,7 @@
{ {
"id": "da46d875-6b82-4681-9284-653b0c7ae241", "id": "da46d875-6b82-4681-9284-653b0c7ae241",
"snapshot": "chrome", "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", "source": "test_task_2",
"config": [ "config": [
{ {
@@ -100,4 +100,3 @@
] ]
} }
} }