The evolution of Retrieval-Augmented Generation (RAG) has shifted from static retrieval pipelines to dynamic, agentic workflows where a central planner orchestrates multi-turn reasoning. However, existing paradigms face a critical dichotomy: they either optimize modules jointly within rigid, fixed-graph architectures, or empower dynamic planning while treating executors as frozen, black-box tools. We identify that this \textit{decoupled optimization} creates a ``strategic-operational mismatch,'' where sophisticated planning strategies fail to materialize due to unadapted local executors, often leading to negative performance gains despite increased system complexity. In this paper, we propose \textbf{JADE} (\textbf{J}oint \textbf{A}gentic \textbf{D}ynamic \textbf{E}xecution), a unified framework for the joint optimization of planning and execution within dynamic, multi-turn workflows. By modeling the system as a cooperative multi-agent team unified under a single shared backbone, JADE enables end-to-end learning driven by outcome-based rewards. This approach facilitates \textit{co-adaptation}: the planner learns to operate within the capability boundaries of the executors, while the executors evolve to align with high-level strategic intent. Empirical results demonstrate that JADE transforms disjoint modules into a synergistic system, yielding remarkable performance improvements via joint optimization and enabling a flexible balance between efficiency and effectiveness through dynamic workflow orchestration.

翻译：检索增强生成（RAG）的发展已从静态检索流水线转向动态的智能工作流，其中央规划器协调多轮推理。然而，现有范式面临一个关键的两难困境：它们要么在僵化、固定图架构内联合优化各模块，要么在赋予动态规划能力的同时将执行器视为冻结的黑盒工具。我们发现，这种“解耦优化”造成了“战略与执行不匹配”——由于局部执行器未能适配，复杂的规划策略无法有效落实，往往导致系统复杂性增加而性能增益反而下降。本文提出 **JADE**（**J**oint **A**gentic **D**ynamic **E**xecution），一个在动态多轮工作流中实现规划与执行联合优化的统一框架。通过将系统建模为在单一共享主干网络下统一协作的多智能体团队，JADE支持基于结果奖励的端到端学习。这种方法促进了“协同适应”：规划器学会在执行器能力边界内运作，而执行器则不断演进以对齐高层战略意图。实证结果表明，JADE将分离的模块转化为协同系统，通过联合优化带来显著的性能提升，并借助动态工作流编排实现了效率与效果之间的灵活平衡。