feat:任务过程探索分支提示词优化

This commit is contained in:
liailing1026
2026-01-16 11:11:57 +08:00
parent 029df6b5a5
commit 571b5101ff

View File

@@ -57,27 +57,40 @@ Note: "Modification Requirement" specifies how to modify the "Baseline Completio
"ID": "Action4", "ID": "Action4",
"ActionType": "Propose", "ActionType": "Propose",
"AgentName": "Mia", "AgentName": "Mia",
"Description": "Propose psychological theories on love and attachment that could be applied to AI's emotional development.", "Description": "提议关于人工智能情感发展的心理学理论,重点关注爱与依恋的概念。",
"ImportantInput": [ "ImportantInput": [
"InputObject:Story Outline" "InputObject:Story Outline"
] ]
}}, }},
{{ {{
"ID": "Action5", "ID": "Action5",
"ActionType": "Propose", "ActionType": "Critique",
"AgentName": "Noah", "AgentName": "Noah",
"Description": "Propose ethical considerations and philosophical questions regarding AI's capacity for love.", "Description": "对Mia提出的心理学理论进行批判性评估分析其在AI情感发展场景中的适用性和局限性。",
"ImportantInput": [] "ImportantInput": [
"ActionResult:Action4"
]
}}, }},
{{ {{
"ID": "Action6", "ID": "Action6",
"ActionType": "Finalize", "ActionType": "Improve",
"AgentName": "Liam", "AgentName": "Liam",
"Description": "Combine the poetic elements and ethical considerations into a cohesive set of core love elements for the story.", "Description": "基于Noah的批判性反馈改进和完善心理学理论框架使其更贴合AI情感发展的实际需求。",
"ImportantInput": [ "ImportantInput": [
"ActionResult:Action1", "ActionResult:Action4",
"ActionResult:Action5" "ActionResult:Action5"
] ]
}},
{{
"ID": "Action7",
"ActionType": "Finalize",
"AgentName": "Mia",
"Description": "综合所有提议、批判和改进意见整合并提交最终的AI情感发展心理学理论框架。",
"ImportantInput": [
"ActionResult:Action4",
"ActionResult:Action5",
"ActionResult:Action6"
]
}} }}
] ]
}} }}
@@ -86,7 +99,12 @@ Note: "Modification Requirement" specifies how to modify the "Baseline Completio
ImportantInput: Specify if there is any previous result that should be taken special consideration during the execution the action. Should be of format "InputObject:xx" or "ActionResult:xx". ImportantInput: Specify if there is any previous result that should be taken special consideration during the execution the action. Should be of format "InputObject:xx" or "ActionResult:xx".
InputObject_List: List existing objects that should be utilized in current step. InputObject_List: List existing objects that should be utilized in current step.
AgentName: Specify the agent who will perform the action, You CAN ONLY USE THE NAME APPEARS IN "AgentInvolved". AgentName: Specify the agent who will perform the action, You CAN ONLY USE THE NAME APPEARS IN "AgentInvolved".
ActionType: Specify the type of action, note that only the last action can be of type "Finalize", and the last action must be "Finalize". ActionType: Specify the type of action. **CRITICAL REQUIREMENTS:**
1. The "Remaining Steps" MUST include ALL FOUR action types in the following order: Propose -> Critique -> Improve -> Finalize
2. Each action type (Propose, Critique, Improve, Finalize) MUST appear at least once
3. The actions must follow the sequence: Propose actions first, then Critique actions, then Improve actions, and Finalize must be the last action
4. Even if only one agent is involved in a phase, that phase must still have its corresponding action type
5. The last action must ALWAYS be of type "Finalize"
""" """