# JADE: Bridging the Strategic-Operational Gap in Dynamic Agentic RAG

arXiv: https://arxiv.org/abs/2601.21916 · HTML: https://mlsanity.com/paper/2601.21916/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Agentic RAG, agents and memory, one of 15 directions in Retrieval-augmented generation.
- Builds on 31 of its 40 references that are in the map.
- First posted on arXiv 29 Jan 2026.

## Placed in

- Retrieval-augmented generation / [Agentic RAG, agents and memory](https://mlsanity.com/rag/agentic-rag-agents-and-memory/)
- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 30 of 31)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments](https://mlsanity.com/paper/1706.02275/) (2017)
- [Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning](https://mlsanity.com/paper/2503.09516/) (2025)
- [Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps](https://mlsanity.com/paper/2011.01060/) (2020)
- [Text Embeddings by Weakly-Supervised Contrastive Pre-training](https://mlsanity.com/paper/2212.03533/) (2022)
- [Measuring and Narrowing the Compositionality Gap in Language Models](https://mlsanity.com/paper/2210.03350/) (2022)
- [The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games](https://mlsanity.com/paper/2103.01955/) (2021)
- [Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions](https://mlsanity.com/paper/2212.10509/) (2022)
- [MuSiQue: Multihop Questions via Single-hop Question Composition](https://mlsanity.com/paper/2108.00573/) (2021)
- [Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2003.08839/) (2020)
- [Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexity](https://mlsanity.com/paper/2403.14403/) (2024)
- [AmbigQA: Answering Ambiguous Open-domain Questions](https://mlsanity.com/paper/2004.10645/) (2020)
- [R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2503.05592/) (2025)
- [DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environments](https://mlsanity.com/paper/2504.03160/) (2025)
- [Query Rewriting for Retrieval-Augmented Large Language Models](https://mlsanity.com/paper/2305.14283/) (2023)
- [InstructRAG: Instructing Retrieval-Augmented Generation via Self-Synthesized Rationales](https://mlsanity.com/paper/2406.13629/) (2024)
- [Bridging the Preference Gap between Retrievers and LLMs](https://mlsanity.com/paper/2401.06954/) (2024)
- [LongRAG: A Dual-Perspective Retrieval-Augmented Generation Paradigm for Long-Context Question Answering](https://mlsanity.com/paper/2410.18050/) (2024)
- [s3: You Don't Need That Much Data to Train a Search Agent via RL](https://mlsanity.com/paper/2505.14146/) (2025)
- [Retrieve, Summarize, Plan: Advancing Multi-hop Question Answering with an Iterative Approach](https://mlsanity.com/paper/2407.13101/) (2024)
- [Improving Retrieval-Augmented Generation through Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2501.15228/) (2025)
- [R1-Searcher++: Incentivizing the Dynamic Knowledge Acquisition of LLMs via Reinforcement Learning](https://mlsanity.com/paper/2505.17005/) (2025)
- [Improving Retrieval Augmented Language Model with Self-Reasoning](https://mlsanity.com/paper/2407.19813/) (2024)
- [Deep Research: A Systematic Survey](https://mlsanity.com/paper/2512.02038/) (2025)
- [On Group Relative Policy Optimization Collapse in Agent Search: The Lazy Likelihood-Displacement](https://mlsanity.com/paper/2512.04220/) (2025)
- [PTDE: Personalized Training with Distilled Execution for Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2210.08872/) (2022)
- [Beyond Monolithic Architectures: A Multi-Agent Search and Knowledge Optimization Framework for Agentic Search](https://mlsanity.com/paper/2601.04703/) (2026)

## Built on by (most cited first, 6 of 6)

- [SoK: Agentic Retrieval-Augmented Generation (RAG): Taxonomy, Architectures, Evaluation, and Research Directions](https://mlsanity.com/paper/2603.07379/) (2026)
- [OASES: Outcome-Aligned Search-Evaluation Co-Training for Agentic Search](https://mlsanity.com/paper/2604.03675/) (2026)
- [UnityMAS-O: A General RL Optimization Framework for LLM-Based Multi-Agent Systems](https://mlsanity.com/paper/2605.26646/) (2026)
- [SearchArt: Training Long-Horizon Search Agent with Scalable Synthetic and Verified Task](https://mlsanity.com/paper/2607.24850/) (2026)
- [VaseMuseum: Digital Intelligent Museum for Ancient Greek Pottery](https://mlsanity.com/paper/2607.06374/) (2026)
- [CoSkill: Joint Reinforcement Learning of Reasoning and Meta-Skill Agents for Hierarchical Skill Evolution](https://mlsanity.com/paper/2609.04865/) (2026)

## Abstract (arXiv)

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 textitdecoupled 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 JADE (Joint Agentic Dynamic Execution), 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 textitco-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.