JADE: Bridging the Strategic-Operational Gap in Dynamic Agentic RAG
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908798230200320 |
|---|---|
| author | Chen, Yiqun Zhang, Erhan Hu, Tianyi Wang, Shijie Yang, Zixuan Zhong, Meizhi Wei, Xiaochi Gao, Yan Wu, Yi Hu, Yao Mao, Jiaxin |
| author_facet | Chen, Yiqun Zhang, Erhan Hu, Tianyi Wang, Shijie Yang, Zixuan Zhong, Meizhi Wei, Xiaochi Gao, Yan Wu, Yi Hu, Yao Mao, Jiaxin |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_21916 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | JADE: Bridging the Strategic-Operational Gap in Dynamic Agentic RAG Chen, Yiqun Zhang, Erhan Hu, Tianyi Wang, Shijie Yang, Zixuan Zhong, Meizhi Wei, Xiaochi Gao, Yan Wu, Yi Hu, Yao Mao, Jiaxin Artificial Intelligence Computation and Language Information Retrieval 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. |
| title | JADE: Bridging the Strategic-Operational Gap in Dynamic Agentic RAG |
| topic | Artificial Intelligence Computation and Language Information Retrieval |
| url | https://arxiv.org/abs/2601.21916 |