mlsanityData to 14 Oct 2026

MedAgent-Pro: Towards Evidence-based Multi-modal Medical Diagnosis via Reasoning Agentic Workflow

arXiv 2503.18968 ↗First posted 21 Mar 2025cs.AIcited by 73

On the map: LLM reasoning → Clinical and biomedical applications

also in 1 more
Abstract (arXiv)

In modern medicine, clinical diagnosis relies on the comprehensive analysis of primarily textual and visual data, drawing on medical expertise to ensure systematic and rigorous reasoning. Recent advances in large Vision-Language Models (VLMs) and agent-based methods hold great potential for medical diagnosis, thanks to the ability to effectively integrate multi-modal patient data. However, they often provide direct answers and draw empirical-driven conclusions without quantitative analysis, which reduces their reliability and clinical usability. We propose MedAgent-Pro, a new agentic reasoning paradigm that follows the diagnosis principle in modern medicine, to decouple the process into sequential components for step-by-step, evidence-based reasoning. Our MedAgent-Pro workflow presents a hierarchical diagnostic structure to mirror this principle, consisting of disease-level standardized plan generation and patient-level personalized step-by-step reasoning. To support disease-level planning, an RAG-based agent is designed to retrieve medical guidelines to ensure alignment with clinical standards. For patient-level reasoning, we propose to integrate professional tools such as visual models to enable quantitative assessments. Meanwhile, we propose to verify the reliability of each step to achieve evidence-based diagnosis, enforcing rigorous logical reasoning and a well-founded conclusion. Extensive experiments across a wide range of anatomical regions, imaging modalities, and diseases demonstrate the superiority of MedAgent-Pro to mainstream VLMs, agentic systems and state-of-the-art expert models. Ablation studies and human evaluation by clinical experts further validate its robustness and clinical relevance. Code is available at https://github.com/jinlab-imvr/MedAgent-Pro.

Key facts. Cited by 73 papers in the map (data through 14 Oct 2026). Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning. Builds on 56 of its 96 references that are in the map. First posted on arXiv 21 Mar 2025.

Builds on

56 of 96 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoning16 Nov

Other references · 55

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  2. 2023GPT-4 Technical Reportcited by 18,396
  3. 2023Visual Instruction Tuningcited by 7,869
  4. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  5. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  6. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,234
  7. 2023InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Taskscited by 2,565
  8. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,348
  9. 2022Large Language Models Encode Clinical Knowledgecited by 1,830
  10. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Societycited by 1,395
  11. 2023LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Daycited by 1,305
  12. 2022Inner Monologue: Embodied Reasoning through Planning with Language Modelscited by 1,081
38 more
  1. 2025Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scalingcited by 812
  2. 2023ChemCrow: Augmenting large-language models with chemistry toolscited by 631
  3. 2023BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairscited by 520
  4. 2023Medical SAM Adapter: Adapting Segment Anything Model for Medical Image Segmentationcited by 490
  5. 2020PathVQA: 30000+ Questions for Medical Visual Question Answeringcited by 475
  6. 2021SLAKE: A Semantically-Labeled Knowledge-Enhanced Dataset for Medical Visual Question Answeringcited by 449
  7. 2022Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Taskcited by 431
  8. 2023Med-Flamingo: a Multimodal Medical Few-shot Learnercited by 392
  9. 2023PMC-VQA: Visual Instruction Tuning for Medical Visual Question Answeringcited by 338
  10. 2021Big Self-Supervised Models Advance Medical Image Classificationcited by 320
  11. 2024VisionZip: Longer is Better but Not Necessary in Vision Language Modelscited by 313
  12. 2023TidyBot: Personalized Robot Assistance with Large Language Modelscited by 221
  13. 2023AutoAgents: A Framework for Automatic Agent Generationcited by 216
  14. 2024MDAgents: An Adaptive Collaboration of LLMs for Medical Decision-Makingcited by 163
  15. 2024Medical SAM 2: Segment medical images as video via Segment Anything Model 2cited by 154
  16. 2024MAIRA-2: Grounded Radiology Report Generationcited by 145
  17. 2023Emergent autonomous scientific research capabilities of large language modelscited by 132
  18. 2024MMedAgent: Learning to Use Medical Tools with Multi-modal Agentcited by 109
  19. 2023ProAgent: Building Proactive Cooperative Agents with Large Language Modelscited by 98
  20. 2024Large Language Models and Games: A Survey and Roadmapcited by 93
  21. 2023Understanding the Benefits and Challenges of Using Large Language Model-based Conversational Agents for Mental Well-being Supportcited by 75
  22. 2025MedRAX: Medical Reasoning Agent for Chest X-raycited by 70
  23. 2021MMBERT: Multimodal BERT Pretraining for Improved Medical VQAcited by 68
  24. 2024A Framework for Human Evaluation of Large Language Models in Healthcare Derived from Literature Reviewcited by 66
  25. 2024ProtAgents: Protein discovery via large language model multi-agent collaborations combining physics and machine learningcited by 64
  26. 2021nnDetection: A Self-configuring Method for Medical Object Detectioncited by 60
  27. 2020FocalMix: Semi-Supervised Learning for 3D Medical Image Detectioncited by 52
  28. 2023Data-Efficient Image Quality Assessment with Attention-Panel Decodercited by 49
  29. 2023CGMI: Configurable General Multi-Agent Interaction Frameworkcited by 42
  30. 2023Towards autonomous system: flexible modular production system enhanced with large language model agentscited by 39
  31. 2025PathFinder: A Multi-Modal Multi-Agent System for Medical Diagnostic Decision-Making Applied to Histopathologycited by 39
  32. 2022REFUGE2 Challenge: A Treasure Trove for Multi-Dimension Analysis and Evaluation in Glaucoma Screeningcited by 38
  33. 2023Improving Grounded Language Understanding in a Collaborative Environment by Interacting with Agents Through Help Feedbackcited by 32
  34. 2024CT-GLIP: 3D Grounded Language-Image Pretraining with CT Scans and Radiology Reports for Full-Body Scenarioscited by 30
  35. 2024KG4Diagnosis: A Hierarchical Multi-Agent LLM Framework with Knowledge Graph Enhancement for Medical Diagnosiscited by 26
  36. 2021Superpixel-guided Iterative Learning from Noisy Labels for Medical Image Segmentationcited by 25
  37. 2023Domain generalization across tumor types, laboratories, and species -- insights from the 2022 edition of the Mitosis Domain Generalization Challengecited by 25
  38. 2024VisionUnite: A Vision-Language Foundation Model for Ophthalmology Enhanced with Clinical Knowledgecited by 19

50 most cited of 55 All 55 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 15; 2026: 58.

73 papers.

Sort:

By area:

  1. 2025Lingshu: A Generalist Foundation Model for Unified Multimodal Medical Understanding and Reasoningcited by 230
  2. 2025A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deploymentcited by 116
  3. 2025A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challengescited by 62
  4. 2025LLM-based Agents Suffer from Hallucinations: A Survey of Taxonomy, Methods, and Directionscited by 50
  5. 2026A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agentscited by 50
  6. 2025VisionThink: Smart and Efficient Vision Language Model via Reinforcement Learningcited by 43
  7. 2025PathAgent: Toward Interpretable Analysis of Whole-slide Pathology Images via Large Language Model-based Agentic Reasoningcited by 19
  8. 2025Ophiuchus: Incentivizing Tool-augmented "Think with Images" for Joint Medical Segmentation, Understanding and Reasoningcited by 10
  9. 2026MedSAM-Agent: Empowering Interactive Medical Image Segmentation with Multi-turn Agentic Reinforcement Learningcited by 8
  10. 2026PathReasoner-R1: Instilling Structured Reasoning into Pathology Vision-Language Model via Knowledge-Guided Policy Optimizationcited by 7
  11. 2025MTBBench: A Multimodal Sequential Clinical Decision-Making Benchmark in Oncologycited by 6
  12. 2026Evo-MedAgent: Beyond One-Shot Diagnosis with Agents That Remember, Reflect, and Improvecited by 6
38 more
  1. 2026RadAgent: A tool-using AI agent for stepwise interpretation of chest computed tomographycited by 6
  2. 2026AgenticRed: Evolving Agentic Systems for Red-Teamingcited by 5
  3. 20263DMedAgent: Unified Perception-to-Understanding for 3D Medical Analysiscited by 5
  4. 2026MedOpenClaw and MedFlowBench: Auditing Medical Agents in Full-Study Workflowscited by 5
  5. 2025AT-CXR: Uncertainty-Aware Agentic Triage for Chest X-rayscited by 4
  6. 2025LungNoduleAgent: A Collaborative Multi-Agent System for Precision Diagnosis of Lung Nodulescited by 4
  7. 2026MEDVISTAGYM: A Scalable Training Environment for Thinking with Medical Images via Tool-Integrated Reinforcement Learningcited by 4
  8. 2026Experience-Driven Multi-Agent Systems Are Training-free Context-aware Earth Observerscited by 4
  9. 2026OPGAgent: An Agent for Auditable Dental Panoramic X-ray Interpretationcited by 4
  10. 2025CARES: Collaborative Agentic Reasoning for Error Detection in Surgerycited by 3
  11. 2026Strong Reasoning Isn't Enough: Evaluating Evidence Elicitation in Interactive Diagnosiscited by 3
  12. 2026Joint Optimization of Reasoning and Dual-Memory for Self-Learning Diagnostic Agentcited by 3
  13. 2026OralAgent: Integrating Reasoning, Tools, and Knowledge for Interactive Dental Image Analysiscited by 3
  14. 2026MedCTA: A Benchmark for Clinical Tool Agentscited by 3
  15. 2026ClinFusion: A Vision-Centric Multimodal LLM System for Holistic Medical Understandingcited by 3
  16. 2025CardAIc-Agents: A Multimodal Framework with Hierarchical Adaptation for Cardiac Care Supportcited by 2
  17. 2026MedScope: Incentivizing "Think with Videos" for Clinical Reasoning via Coarse-to-Fine Tool Callingcited by 2
  18. 2026Computational Pathology in the Era of Emerging Foundation and Agentic AI -- International Expert Perspectives on Clinical Integration and Translational Readinesscited by 2
  19. 2026LatentDx: Latent Multi-Agent Communication for Cross-Hospital Rare-Disease Diagnosiscited by 2
  20. 2026The Path to Self-Evolving Clinical Systems: Scaling Medical Agents from Assistance to Autonomycited by 2
  21. 2026MedClaw: Heuristic Agent Harness for Long-Horizon Surgical Video Reasoningcited by 2
  22. 2026EviDx: Evidence-Aware Active Diagnosis with Scaffolded LLM Agentscited by 2
  23. 2025A Multi-Agent System for Complex Reasoning in Radiology Visual Question Answeringcited by 1
  24. 2025SpineBench: A Clinically Salient, Level-Aware Benchmark Powered by the SpineMed-450k Corpuscited by 1
  25. 2025Colon-X: Advancing Intelligent Colonoscopy toward Clinical Reasoningcited by 1
  26. 2026Agentic AI in Healthcare & Medicine: A Seven-Dimensional Taxonomy for Empirical Evaluation of LLM-based Agentscited by 1
  27. 2026EviAgent: Evidence-Driven Agent for Radiology Report Generationcited by 1
  28. 2026MedProbeBench: Systematic Benchmarking at Deep Evidence Integration for Expert-level Medical Guidelinecited by 1
  29. 2026Thinking Like a Clinician: A Cognitive AI Agent for Clinical Diagnosis via Panoramic Profiling and Adversarial Debatecited by 1
  30. 2026MedScribe: Clinically Grounded CT Reporting through Agentic Workflowscited by 1
  31. 2026Beyond English benchmarks: clinical llm evaluation in Brazilian Portuguesecited by 1
  32. 2026Aligning Clinical Needs and AI Capabilities: A Survey on LLMs for Medical Reasoningcited by 1
  33. 2026Policy-Driven CT-Agent: Modeling Phase-Aware Diagnostic Control for Clinically Consistent CT Reasoningcited by 1
  34. 2026CoMMa: Contribution-Aware Medical Multi-Agents for Decentralized Oncology Decision Supportcited by 0
  35. 2026Process-Supervised Multi-Agent Reinforcement Learning for Reliable Clinical Reasoningcited by 0
  36. 2026MedCollab: IBIS-Guided Multi-Agent Collaboration with Hierarchical Disease Relation Chains for Clinical Diagnosiscited by 0
  37. 2026MedCoRAG: Interpretable Hepatology Diagnosis via Hybrid Evidence Retrieval and Multispecialty Consensuscited by 0
  38. 2026UltrasoundAgents: Hierarchical Multi-Agent Evidence-Chain Reasoning for Breast Ultrasound Diagnosiscited by 0

50 most cited of 73 All 73 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026DeepLens Diagnosis Agent: Agentic Workflow Design Lets a Small Reasoning Model Compete with Frontier LLMs
  2. 2025MAM: Modular Multi-Agent Framework for Multi-Modal Medical Diagnosis via Role-Specialized Collaboration
  3. 2026MeDxAgent: Multi-Agent Consultation for Interactive Medical Diagnosis
  4. 2025MedicalAgentsBench for Complex Medical Reasoning: Comparing Internalized Reasoning Models versus Externalized Agent-based Frameworks
  5. 2026MDIA: A Multi-Agent Diagnostic Intelligence Pipeline on HealthBench Professional
  6. 2026ClinicalAgents: Multi-Agent Orchestration for Clinical Decision Making with Dual-Memory
  7. 2025Med-VRAgent: A Framework for Medical Visual Reasoning-Enhanced Agents
  8. 2026MedMASLab: A Unified Orchestration Framework for Benchmarking Multimodal Medical Multi-Agent Systems