控制-資料流分離：多智能體LLM中的穩定提示優化

摘要

提示優化可以改善多智能體大型語言模型系統，但被優化的提示往往同時扮演兩個相互糾纏的角色：產生與任務相關的內容，以及指定執行關鍵協定，例如訊息路由、輸出格式化和終止訊號，而底層程式碼依賴這些協定。因此，本意為改善內容生成的提示修改，可能在不經意間破壞協定，導致整個智能體管線失敗。我們的核心觀察是，這兩個角色具有不同的表徵：執行協定通常是結構化的，而與任務相關的內容通常以非結構化語言表達。基於此，我們提出控制流與資料流分離，其中執行關鍵控制以帶型別且經驗證的程式物件表示，而與任務相關的語言則保持為可最佳化的資料流，用於智能體之間的通訊。此設計允許最佳化器在不將路由或格式化介面暴露於提示漂移的情況下改善多智能體行為。在合成推理、協作式審查生成和保險評定工作流程中，我們的框架實驗性地實現了100%的最終協定有效性，同時持續提升任務表現。

English

Prompt optimization can improve multi-agent LLM systems, but the prompts being optimized often serve two entangled roles: generating task-relevant content and specifying execution-critical protocols, such as message routing, output formatting, and termination signals, on which the underlying code relies. As a result, a prompt edit intended to improve content generation can inadvertently corrupt the protocol and cause the entire agent pipeline to fail. Our key observation is that these two roles have different representations: execution protocols are typically structured, while task-relevant content is usually expressed in unstructured language. Based on this, we propose control-data flow separation, where execution-critical control is represented as typed, validated program objects, while task-relevant language remains the optimizable data flow for agent communication. This design allows optimizers to improve multi-agent behavior without exposing the routing or formatting interface to prompt drift. Across synthetic reasoning, collaborative review generation, and insurance rating workflows, our framework empirically achieves 100% eventual protocol validity while consistently improving task performance.