mlsanityData to 7 Oct 2026

Grounded by Experience: Generative Healthcare Prediction Augmented with Hierarchical Agentic Retrieval

arXiv 2511.13293 ↗First posted 17 Nov 2025cs.AIcited by 1

On the map: LLM agents and tool use → Medical and scientific domain agents

Abstract (arXiv)

Accurate healthcare prediction is critical for improving patient outcomes and reducing operational costs. Bolstered by growing reasoning capabilities, large language models (LLMs) offer a promising path to enhance healthcare predictions by drawing on their rich parametric knowledge. However, LLMs are prone to factual inaccuracies due to limitations in the reliability and coverage of their embedded knowledge. While retrieval-augmented generation (RAG) frameworks, such as GraphRAG and its variants, have been proposed to mitigate these issues by incorporating external knowledge, they face two key challenges in the healthcare scenario: (1) identifying the clinical necessity to activate the retrieval mechanism, and (2) achieving synergy between the retriever and the generator to craft contextually appropriate retrievals. To address these challenges, we propose GHAR, a underlinegenerative underlinehierarchical underlineagentic underlineRAG framework that simultaneously resolves when to retrieve and how to optimize the collaboration between submodules in healthcare. Specifically, for the first challenge, we design a dual-agent architecture comprising Agent-Top and Agent-Low. Agent-Top acts as the primary physician, iteratively deciding whether to rely on parametric knowledge or to initiate retrieval, while Agent-Low acts as the consulting service, summarising all task-relevant knowledge once retrieval was triggered. To tackle the second challenge, we innovatively unify the optimization of both agents within a formal Markov Decision Process, designing diverse rewards to align their shared goal of accurate prediction while preserving their distinct roles. Extensive experiments on three benchmark datasets across three popular tasks demonstrate our superiority over state-of-the-art baselines, highlighting the potential of hierarchical agentic RAG in advancing healthcare systems.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use. Builds on 40 of its 64 references that are in the map. First posted on arXiv 17 Nov 2025.

Builds on

40 of 64 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025MedAgentBoard: Benchmarking Multi-Agent Collaboration with Conventional Methods for Diverse Medical Tasks18 May
  2. 2024ColaCare: Enhancing Electronic Health Record Modeling through Large Language Model-Driven Multi-Agent Collaboration3 Oct

Other references · 38

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,146
  3. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  4. 2017Billion-scale similarity search with GPUscited by 2,477
  5. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,582
  6. 2022Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?cited by 1,413
  7. 2025Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learningcited by 1,371
  8. 2024M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillationcited by 1,050
  9. 2021The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Gamescited by 903
  10. 2024A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Modelscited by 450
  11. 2024Multilingual E5 Text Embeddings: A Technical Reportcited by 357
  12. 2024LightRAG: Simple and Fast Retrieval-Augmented Generationcited by 310
26 more
  1. 2024BioMistral: A Collection of Open-Source Pretrained Large Language Models for Medical Domainscited by 299
  2. 2023MEDITRON-70B: Scaling Medical Pretraining for Large Language Modelscited by 272
  3. 2025Agentic Retrieval-Augmented Generation: A Survey on Agentic RAGcited by 242
  4. 2020A Survey on Heterogeneous Graph Embedding: Methods, Techniques, Applications and Sourcescited by 126
  5. 2023When MOE Meets LLMs: Parameter Efficient Fine-tuning for Multi-task Medical Applicationscited by 110
  6. 2018Deep Reinforcement Learning for Page-wise Recommendationscited by 99
  7. 2025MedRAG: Enhancing Retrieval-augmented Generation with Knowledge Graph-Elicited Reasoning for Healthcare Copilotcited by 83
  8. 2023GraphCare: Enhancing Healthcare Predictions with Personalized Knowledge Graphscited by 57
  9. 2020StageNet: Stage-Aware Neural Networks for Health Risk Predictioncited by 47
  10. 2024Reasoning-Enhanced Healthcare Predictions with Knowledge Graph Community Retrievalcited by 45
  11. 2024Modular RAG: Transforming RAG Systems into LEGO-like Reconfigurable Frameworkscited by 41
  12. 2025Improving Retrieval-Augmented Generation through Multi-Agent Reinforcement Learningcited by 39
  13. 2024M-RAG: Reinforcing Large Language Model Performance through Retrieval-Augmented Generation with Multiple Partitionscited by 38
  14. 2024GLBench: A Comprehensive Benchmark for Graph with Large Language Modelscited by 36
  15. 2024ClinicalBench: Can LLMs Beat Traditional ML Models in Clinical Prediction?cited by 31
  16. 2022Pessimism in the Face of Confounders: Provably Efficient Offline Reinforcement Learning in Partially Observable Markov Decision Processescited by 26
  17. 2025G-Refer: Graph Retrieval-Augmented Large Language Model for Explainable Recommendationcited by 26
  18. 2024EMERGE: Enhancing Multimodal Electronic Health Records Predictive Modeling with Retrieval-Augmented Generationcited by 16
  19. 2021Drug Package Recommendation via Interaction-aware Graph Inductioncited by 14
  20. 2025Towards Omni-RAG: Comprehensive Retrieval-Augmented Generation for Large Language Models in Medical Applicationscited by 13
  21. 2024RouterRetriever: Routing over a Mixture of Expert Embedding Modelscited by 12
  22. 2023SHAPE: A Sample-adaptive Hierarchical Prediction Network for Medication Recommendationcited by 7
  23. 2022Heterogeneous Graph Contrastive Learning with Meta-path Contexts and Adaptively Weighted Negative Samplescited by 6
  24. 2024FlexCare: Leveraging Cross-Task Synergy for Flexible Multimodal Healthcare Predictioncited by 6
  25. 2025Unveiling Discrete Clues: Superior Healthcare Predictions for Rare Diseasescited by 5
  26. 2023MedDiffusion: Boosting Health Risk Prediction via Diffusion-based Data Augmentationcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Fusion and Alignment Enhancement with Large Language Models for Tail-item Sequential Recommendationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Generative AI for Healthcare: Fundamentals, Challenges, and Perspectives
  2. 2026Efficient and Effective Internal Memory Retrieval for LLM-Based Healthcare Prediction
  3. 2026AgentRx: A Benchmark Study of LLM Agents for Multimodal Clinical Prediction Tasks
  4. 2026SEMA-RAG: A Self-Evolving Multi-Agent Retrieval-Augmented Generation Framework for Medical Reasoning
  5. 2025Leveraging Language Models and RAG for Efficient Knowledge Discovery in Clinical Environments
  6. 2026Retrieval-Augmented Agentic Rubric Generation for Reliable Medical Response Evaluation
  7. 2026A corpus-specific clinical RAG system matches or outperforms newer frontier LLMs on HealthBench
  8. 2025Talk Before You Retrieve: Agent-Led Discussions for Better RAG in Medical QA