trace_synthesis/tasks/10.json
yuyr a84d51a101 1. 增加r1生成综合策略代码和输出;
2. 增加tasks;
3. 增加analysis部分,对策略进行归纳分类,然后进行评测。
2025-04-17 17:40:15 +08:00

34 lines
1.4 KiB
JSON

{
"sites": [
"map"
],
"task_id": 10,
"require_login": true,
"storage_state": null,
"start_url": "https://www.openstreetmap.org",
"geolocation": null,
"intent_template": "Tell me the full address of all {{airport_type}} that are within a driving distance of {{radius}} to {{start}}",
"instantiation_dict": {
"airport_type": "US international airports",
"start": "Niagara Falls",
"radius": "60 km"
},
"intent": "Tell me the full address of all US international airports that are within a driving distance of 60 km to Niagara Falls",
"require_reset": false,
"eval": {
"eval_types": [
"string_match"
],
"reference_answers": {
"must_include": [
"Niagara Falls International Airport, 2035, Niagara Falls Boulevard, City of Niagara Falls, Town of Wheatfield, Niagara County, New York, 14304, United States",
"Buffalo-Niagara International Airport, Holtz Drive, Town of Cheektowaga, Erie County, New York, 14225, United States"
]
},
"reference_url": "",
"program_html": [],
"string_note": "",
"reference_answer_raw_annotation": "Niagara Falls International Airport, 2035, Niagara Falls Boulevard, City of Niagara Falls, Town of Wheatfield, Niagara County, New York, 14304, United States Buffalo-Niagara International Airport, South Youngs Road, Town of Cheektowaga, Erie County, New York, 14221, United States"
},
"intent_template_id": 79
}