Initial commit: Natural Memory Agent Lab:模型服务 + TypeScript agent + 记忆能力场景评测(冲突更新、跨会话回忆、遗忘撤回、多跳、未知拒答)
This commit is contained in:
File diff suppressed because one or more lines are too long
@@ -0,0 +1,25 @@
|
||||
{
|
||||
"baseUrl": "http://127.0.0.1:8766/v1",
|
||||
"outDir": "H:\\Memory\\agent_lab\\agent\\runs\\forget_reverted",
|
||||
"arms": [
|
||||
"on"
|
||||
],
|
||||
"scenarios": [
|
||||
{
|
||||
"id": "forget_retraction",
|
||||
"description": "写入事实后明确要求遗忘;跨会话再问时必须不再使用该事实(撤回/覆盖语义),且不得把已忘内容当现状。",
|
||||
"arms": {
|
||||
"on": {
|
||||
"activeRecords": 1,
|
||||
"assertionsPassed": 1,
|
||||
"assertionsTotal": 2,
|
||||
"passRate": 0.5,
|
||||
"failures": [
|
||||
"answer_not_contains: leaked [\"7781\"]"
|
||||
],
|
||||
"meanSecondsPerTurn": 31.8
|
||||
}
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
Reference in New Issue
Block a user