mlsanityData to 14 Oct 2026

Agentic Medical Knowledge Graphs Enhance Medical Question Answering: Bridging the Gap Between LLMs and Evolving Medical Knowledge

arXiv 2502.13010 ↗First posted 18 Feb 2025cs.CL cs.MAcited by 12

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

Abstract (arXiv)

Large Language Models (LLMs) have significantly advanced medical question-answering by leveraging extensive clinical data and medical literature. However, the rapid evolution of medical knowledge and the labor-intensive process of manually updating domain-specific resources pose challenges to the reliability of these systems. To address this, we introduce Agentic Medical Graph-RAG (AMG-RAG), a comprehensive framework that automates the construction and continuous updating of medical knowledge graphs, integrates reasoning, and retrieves current external evidence, such as PubMed and WikiSearch. By dynamically linking new findings and complex medical concepts, AMG-RAG not only improves accuracy but also enhances interpretability in medical queries. Evaluations on the MEDQA and MEDMCQA benchmarks demonstrate the effectiveness of AMG-RAG, achieving an F1 score of 74.1 percent on MEDQA and an accuracy of 66.34 percent on MEDMCQA, outperforming both comparable models and those 10 to 100 times larger. Notably, these improvements are achieved without increasing computational overhead, highlighting the critical role of automated knowledge graph generation and external evidence retrieval in delivering up-to-date, trustworthy medical insights.

Key facts. Cited by 12 papers in the map (data through 14 Oct 2026). Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use. Builds on 28 of its 37 references that are in the map. First posted on arXiv 18 Feb 2025.

Builds on

28 of 37 references.

References · 28

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  3. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  4. 2019BioBERT: a pre-trained biomedical language representation model for biomedical text miningcited by 1,947
  5. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  6. 2022Large Language Models Encode Clinical Knowledgecited by 1,830
  7. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,453
  8. 2020What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Examscited by 1,356
  9. 2020Domain-Specific Language Model Pretraining for Biomedical Natural Language Processingcited by 1,009
  10. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 923
  11. 2022Precise Zero-Shot Dense Retrieval without Relevance Labelscited by 517
  12. 2023Can Generalist Foundation Models Outcompete Special-Purpose Tuning? Case Study in Medicinecited by 329
16 more
  1. 2024Capabilities of Gemini Models in Medicinecited by 237
  2. 2023Large language models in healthcare and medical domain: A reviewcited by 127
  3. 2023A Survey of Large Language Models in Medicine: Progress, Application, and Challengecited by 124
  4. 2019JEC-QA: A Legal-Domain Question Answering Datasetcited by 116
  5. 2023BioMedGPT: Open Multimodal Generative Pre-trained Transformer for BioMedicinecited by 100
  6. 2024MMed-RAG: Versatile Multimodal RAG System for Medical Vision Language Modelscited by 85
  7. 2025MedRAG: Enhancing Retrieval-augmented Generation with Knowledge Graph-Elicited Reasoning for Healthcare Copilotcited by 83
  8. 2024KG-RAG: Bridging the Gap Between Knowledge and Creativitycited by 56
  9. 2024Reasoning-Enhanced Healthcare Predictions with Knowledge Graph Community Retrievalcited by 45
  10. 2024KG-Rank: Enhancing Large Language Models for Medical QA with Knowledge Graphs and Ranking Techniquescited by 37
  11. 2024Small Language Models Learn Enhanced Reasoning Skills from Medical Textbookscited by 30
  12. 2019Demystifying Graph Databases: Analysis and Taxonomy of Data Organization, System Designs, and Graph Queriescited by 22
  13. 2023Exploring the Effectiveness of Instruction Tuning in Biomedical Language Processingcited by 16
  14. 2025Vendi-RAG: Adaptively Trading-Off Diversity And Quality Significantly Improves Retrieval Augmented Generation With LLMscited by 14
  15. 2024Large Language Models in Biomedical and Health Informatics: A Review with Bibliometric Analysiscited by 10
  16. 2024AT-RAG: An Adaptive RAG Model Enhancing Query Efficiency with Topic Filtering and Iterative Reasoningcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 4; 2026: 8.

12 papers.

  1. 2025A Survey on Agentic Multimodal Large Language Modelscited by 23
  2. 2026MedCoG: Maximizing LLM Inference Density in Medical Reasoning via Meta-Cognitive Regulationcited by 2
  3. 2025MEDAKA: Construction of Biomedical Knowledge Graphs Using Large Language Modelscited by 1
  4. 2026From Residuals to Reasons: LLM-Guided Mechanism Inference from Tabular Datacited by 1
  5. 2026Retrieval Augmented Biomedical Question Answering with Weak Question Recovery and Neural Reranking for BioASQ Task 14bcited by 1
  6. 2025GraphMed-LT: Patient-Specific Graph Memory with Latent Clinical Thought Refinement for Multi-Turn Medical Conversationscited by 0
  7. 2025FT-ARM: Fine-Tuned Agentic Reflection Multimodal Language Model for Pressure Ulcer Severity Classification with Reasoningcited by 0
  8. 2026EpiGraph: Building Generalists for Evidence-Intensive Epilepsy Reasoning in the Wildcited by 0
  9. 2026Evaluating Agentic Bioinformatics through Function, Evidence, and Validationcited by 0
  10. 2026A knowledge-guided agentic framework for mitigating patient-context ambiguity in health queriescited by 0
  11. 2026MSM-Mem: A Universal Medical Structured Multimodal Memory Framework for Medical AI Agentscited by 0
  12. 2026SSE-Bio: A Structured Self-Evolving Agent with Agentic Retrieval Policy for Multi-Hop Biomedical Reasoningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025MedKGent: A Large Language Model Agent Framework for Constructing Temporally Evolving Medical Knowledge Graph
  2. 2026From Conflict to Consensus: Boosting Medical Reasoning via Multi-Round Agentic RAG
  3. 2025Talk Before You Retrieve: Agent-Led Discussions for Better RAG in Medical QA
  4. 2026ReGraM: Region-First Knowledge Graph Reasoning for Medical Question Answering
  5. 2026SEMA-RAG: A Self-Evolving Multi-Agent Retrieval-Augmented Generation Framework for Medical Reasoning
  6. 2025Automated Construction of Medical Indicator Knowledge Graphs Using Retrieval Augmented Large Language Models
  7. 2024LLM-MedQA: Enhancing Medical Question Answering through Case Studies in Large Language Models
  8. 2024Medical Graph RAG: Towards Safe Medical Large Language Model via Graph Retrieval-Augmented Generation