mlsanityData to 7 Oct 2026

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

arXiv 2601.21916 ↗First posted 29 Jan 2026cs.AI cs.CL cs.IRcited by 6

On the map: Retrieval-augmented generation → Agentic RAG, agents and memory

also in 1 more
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.

Key facts. Cited by 6 papers in the map (data through 7 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.

Builds on

31 of 40 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025R1-Searcher++: Incentivizing the Dynamic Knowledge Acquisition of LLMs via Reinforcement Learning22 May
  2. 2025s3: You Don't Need That Much Data to Train a Search Agent via RL20 May
  3. 2025Improving Retrieval-Augmented Generation through Multi-Agent Reinforcement Learning25 Jan

Other references · 28

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  3. 2024Qwen2 Technical Reportcited by 2,076
  4. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,800
  5. 2017Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environmentscited by 1,519
  6. 2025Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learningcited by 1,371
  7. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,259
  8. 2022Text Embeddings by Weakly-Supervised Contrastive Pre-trainingcited by 1,216
  9. 2022Measuring and Narrowing the Compositionality Gap in Language Modelscited by 1,054
  10. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 911
  11. 2021The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Gamescited by 903
  12. 2021MuSiQue: Multihop Questions via Single-hop Question Compositioncited by 893
16 more
  1. 2020Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learningcited by 475
  2. 2024Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexitycited by 437
  3. 2020AmbigQA: Answering Ambiguous Open-domain Questionscited by 385
  4. 2025R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learningcited by 322
  5. 2025DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environmentscited by 268
  6. 2023Query Rewriting for Retrieval-Augmented Large Language Modelscited by 211
  7. 2024InstructRAG: Instructing Retrieval-Augmented Generation via Self-Synthesized Rationalescited by 100
  8. 2024Bridging the Preference Gap between Retrievers and LLMscited by 69
  9. 2024LongRAG: A Dual-Perspective Retrieval-Augmented Generation Paradigm for Long-Context Question Answeringcited by 49
  10. 2024Retrieve, Summarize, Plan: Advancing Multi-hop Question Answering with an Iterative Approachcited by 40
  11. 2024Improving Retrieval Augmented Language Model with Self-Reasoningcited by 28
  12. 2025Deep Research: A Systematic Surveycited by 23
  13. 2025On Group Relative Policy Optimization Collapse in Agent Search: The Lazy Likelihood-Displacementcited by 15
  14. 2022PTDE: Personalized Training with Distilled Execution for Multi-Agent Reinforcement Learningcited by 11
  15. 2026Beyond Monolithic Architectures: A Multi-Agent Search and Knowledge Optimization Framework for Agentic Searchcited by 11
  16. 2025AI-SearchPlanner: Modular Agentic Search via Pareto-Optimal Multi-Objective Reinforcement Learningcited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 6.

6 papers.

  1. 2026SoK: Agentic Retrieval-Augmented Generation (RAG): Taxonomy, Architectures, Evaluation, and Research Directionscited by 7
  2. 2026OASES: Outcome-Aligned Search-Evaluation Co-Training for Agentic Searchcited by 7
  3. 2026UnityMAS-O: A General RL Optimization Framework for LLM-Based Multi-Agent Systemscited by 6
  4. 2026SearchArt: Training Long-Horizon Search Agent with Scalable Synthetic and Verified Taskcited by 2
  5. 2026VaseMuseum: Digital Intelligent Museum for Ancient Greek Potterycited by 0
  6. 2026CoSkill: Joint Reinforcement Learning of Reasoning and Meta-Skill Agents for Hierarchical Skill Evolutioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Experience as a Compass: Multi-agent RAG with Evolving Orchestration and Agent Prompts
  2. 2025DecoupleSearch: Decouple Planning and Search via Hierarchical Reward Modeling
  3. 2025Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges
  4. 2025Interact-RAG: Reason and Interact with the Corpus, Beyond Black-Box Retrieval
  5. 2025MAO-ARAG: Multi-Agent Orchestration for Adaptive Retrieval-Augmented Generation
  6. 2026Agent-UCT: Upper Confidence Bounds Applied to Trees for Agentic Workflow Optimization with Cost-Awareness
  7. 2025Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG
  8. 2026A-RAG: Scaling Agentic Retrieval-Augmented Generation via Hierarchical Retrieval Interfaces