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

Fix examples, and evaluation on Chrome, handle corner cases; Initialize arm support

Browse Source
This commit is contained in:
Timothyxxx
2024-02-26 12:34:27 +08:00
parent 7f81a1ee5a
commit a66b36295a
13 changed files with 361 additions and 200 deletions
Download Patch File Download Diff File Expand all files Collapse all files

52
evaluation_examples/examples/chrome/b070486d-e161-459b-aa2b-ef442d973b92.json
View File

@@ -1,5 +1,5 @@
{
"id": " b070486d-e161-459b-aa2b-ef442d973b92",
"id": "b070486d-e161-459b-aa2b-ef442d973b92",
"snapshot": "chrome",
"instruction": "Show side effects of Tamiflu.",
"source": "online_tasks",
@@ -43,41 +43,19 @@
"chrome"
],
"evaluator": {
"func": "exact_match",
"result": {
"type": "url_dashPart",
"selectors": [
"application[name=Chromium] entry[name=Address\\ and\\ search\\ bar]"
],
"goto_prefix": "https://www.",
"partIndex": -1,
"needDeleteId": false,
"returnType": "string"
},
"expected": {
"type": "rule",
"rules": {
"expected": "tamiflu.html#side-effects"
}
],
"trajectory": "trajectories/",
"related_apps": [
"chrome"
],
"evaluator": {
"func":"exact_match",
"result": {
"type": "url_dashPart",
"goto_prefix": "https://www.",
"partIndex": -1,
"needDeleteId": false,
"returnType": "string"
},
"expected":{
"type": "rule",
"rules":{
"expected": "tamiflu.html#side-effects"
}
"func": "exact_match",
"result": {
"type": "url_dashPart",
"goto_prefix": "https://www.",
"partIndex": -1,
"needDeleteId": false,
"returnType": "string"
},
"expected": {
"type": "rule",
"rules": {
"expected": "tamiflu.html#side-effects"
}
}
}
}
}