mlsanityData to 14 Oct 2026

An Agentic System for Rare Disease Diagnosis with Traceable Reasoning

arXiv 2506.20430 ↗First posted 25 Jun 2025cs.CL cs.AI cs.CVcited by 52

On the map: LLM reasoning → Clinical and biomedical applications

also in 1 more
Abstract (arXiv)

Rare diseases affect over 300 million individuals worldwide, yet timely and accurate diagnosis remains an urgent challenge. Patients often endure a prolonged diagnostic odyssey exceeding five years, marked by repeated referrals, misdiagnoses, and unnecessary interventions, leading to delayed treatment and substantial emotional and economic burdens. Here we present DeepRare, a multi-agent system for rare disease differential diagnosis decision support powered by large language models, integrating over 40 specialized tools and up-to-date knowledge sources. DeepRare processes heterogeneous clinical inputs, including free-text descriptions, structured Human Phenotype Ontology terms, and genetic testing results, to generate ranked diagnostic hypotheses with transparent reasoning linked to verifiable medical evidence. Evaluated across nine datasets from literature, case reports and clinical centres across Asia, North America and Europe spanning 14 medical specialties, DeepRare demonstrates exceptional performance on 3,134 diseases. In human-phenotype-ontology-based tasks, it achieves an average Recall@1 of 57.18%, outperforming the next-best method by 23.79%; in multi-modal tests, it reaches 69.1% compared with Exomiser's 55.9% on 168 cases. Expert review achieved 95.4% agreement on its reasoning chains, confirming their validity and traceability. Our work not only advances rare disease diagnosis but also demonstrates how the latest powerful large-language-model-driven agentic systems can reshape current clinical workflows.

Key facts. Cited by 52 papers in the map (data through 14 Oct 2026). Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning. Builds on 16 of its 90 references that are in the map. First posted on arXiv 25 Jun 2025.

Builds on

16 of 90 references.

References · 16

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  3. 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,224
  4. 2023Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agentscited by 333
  5. 2023MedCPT: Contrastive Pre-trained Transformers with Large-scale PubMed Search Logs for Zero-shot Biomedical Information Retrievalcited by 185
  6. 2024MDAgents: An Adaptive Collaboration of LLMs for Medical Decision-Makingcited by 163
  7. 2025MME-CoT: Benchmarking Chain-of-Thought in Large Multimodal Models for Reasoning Quality, Robustness, and Efficiencycited by 125
  8. 2023Towards Accurate Differential Diagnosis with Large Language Modelscited by 116
  9. 2023Evaluating GPT-4 and ChatGPT on Japanese Medical Licensing Examinationscited by 63
  10. 2024RareBench: Can LLMs Serve as Rare Diseases Specialists?cited by 45
  11. 2025Baichuan-M1: Pushing the Medical Capability of Large Language Modelscited by 43
  12. 2024Towards Evaluating and Building Versatile Large Language Models for Medicinecited by 40
4 more
  1. 2022BioLORD: Learning Ontological Representations from Definitions (for Biomedical Concepts and their Textual Descriptions)cited by 21
  2. 2022PMC-Patients: A Large-scale Dataset of Patient Summaries and Relations for Benchmarking Retrieval-based Clinical Decision Support Systemscited by 17
  3. 2024How Well Can Modern LLMs Act as Agent Cores in Radiology Environments?cited by 10
  4. 2024RareAgents: Autonomous Multi-disciplinary Team for Rare Disease Diagnosis and Treatmentcited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 8; 2026: 44.

52 papers.

Sort:

By area:

  1. 2025MedResearcher-R1: Expert-Level Medical Deep Researcher via A Knowledge-Informed Trajectory Synthesis Frameworkcited by 22
  2. 2025End-to-End Agentic RAG System Training for Traceable Diagnostic Reasoningcited by 10
  3. 2026Qworld: Question-Specific Evaluation Criteria for LLMscited by 8
  4. 2025CXRAgent: Director-Orchestrated Multi-Stage Reasoning for Chest X-Ray Interpretationcited by 7
  5. 2026From Conflict to Consensus: Boosting Medical Reasoning via Multi-Round Agentic RAGcited by 7
  6. 2026Evo-MedAgent: Beyond One-Shot Diagnosis with Agents That Remember, Reflect, and Improvecited by 6
  7. 2026MedOpenClaw and MedFlowBench: Auditing Medical Agents in Full-Study Workflowscited by 5
  8. 2026End-to-end autonomous scientific discovery on a real optical platformcited by 5
  9. 2026QCAgent: An agentic framework for quality-controllable pathology report generation from whole slide imagecited by 4
  10. 2026A Vision-Language Foundation Model for Zero-shot Clinical Collaboration and Automated Concept Discovery in Dermatologycited by 3
  11. 2026Joint Optimization of Reasoning and Dual-Memory for Self-Learning Diagnostic Agentcited by 3
  12. 2025Teaching large language models to reason like expert diagnosticianscited by 2
38 more
  1. 2026Rank-and-Reason: Multi-Agent Collaboration Accelerates Zero-Shot Protein Mutation Predictioncited by 2
  2. 2026Emulating Clinician Cognition via Self-Evolving Deep Clinical Researchcited by 2
  3. 2026A Versatile AI Agent for Rare Disease Diagnosis and Risk Gene Prioritizationcited by 2
  4. 2026An agentic framework for gravitational-wave counterpart association in the multi-messenger eracited by 2
  5. 2026LatentDx: Latent Multi-Agent Communication for Cross-Hospital Rare-Disease Diagnosiscited by 2
  6. 2025LA-MARRVEL: A Knowledge-Grounded, Language-Aware LLM Framework for Clinically Robust Rare Disease Gene Prioritizationcited by 1
  7. 2025Colon-X: Advancing Intelligent Colonoscopy toward Clinical Reasoningcited by 1
  8. 2026Which Tool Response Should I Trust? Tool-Expertise-Aware Chest X-ray Agent with Multimodal Agentic Learningcited by 1
  9. 2026QuantClaw: Precision Where It Matters for OpenClawcited by 1
  10. 2026KISS - Knowledge Infrastructure for Scientific Simulation: A Scaffolding for Agentic Earth Sciencecited by 1
  11. 2026DDX-TRACE: A Benchmark for Medical Diagnostic Trajectories in VLMscited by 1
  12. 2025RDMA: Cost Effective Agent-Driven Rare Disease Mining from Electronic Health Recordscited by 0
  13. 2025Adversarial Robustness in Zero-Shot Learning:An Empirical Study on Class and Concept-Level Vulnerabilitiescited by 0
  14. 2026Multi-Agent Causal Reasoning System for Error Pattern Rule Automation in Vehiclescited by 0
  15. 2026OMGs: A multi-agent system supporting MDT decision-making across the ovarian tumour care continuumcited by 0
  16. 2026An artificial intelligence framework for end-to-end rare disease phenotyping from clinical notes using large language modelscited by 0
  17. 2026FetalAgents: A Multi-Agent System for Fetal Ultrasound Image and Video Analysiscited by 0
  18. 2026Cerebra: A Multidisciplinary AI Board for Multimodal Dementia Characterization and Risk Assessmentcited by 0
  19. 2026Within the MDT Room: Situated in Multidisciplinary Team-Grounded Agent Debate for Clinical Diagnosiscited by 0
  20. 2026Dynamic Decision Learning: Test-Time Evolution for Abnormality Grounding in Rare Diseasescited by 0
  21. 2026Logical Consistency as a Bridge: Improving LLM Hallucination Detection via Label Constraint Modeling between Responses and Self-Judgmentscited by 0
  22. 2026DermAgent: A Self-Reflective Agentic System for Dermatological Image Analysis with Multi-Tool Reasoning and Traceable Decision-Makingcited by 0
  23. 2026When Cases Get Rare: A Retrieval Benchmark for Off-Guideline Clinical Question Answeringcited by 0
  24. 2026RadioMaster: Multi-Agent System for Autonomous Radio Signal Generationcited by 0
  25. 2026Enhancing Decision-Making with Large Language Models through Multi-Agent Fictitious Playcited by 0
  26. 2026A specialized reasoning large language model for accelerating rare disease diagnosis: a randomized AI physician assistance trialcited by 0
  27. 2026DeepBD: A Grounded Agentic Workflow for Variant Prioritization and Diagnosis of Genetic Birth Defectscited by 0
  28. 2026RareDxR1: Autonomous Medical Reasoning for Rare Disease Diagnosis Beyond Human Annotationcited by 0
  29. 2026A safety-oriented hypothetico-deductive framework for AI-assisted differential diagnosiscited by 0
  30. 2026Evidence-Grounded AI for Musculoskeletal Carecited by 0
  31. 2026MechAInistic: An LLM-guided Multi-Agent System for Reasoning over Genome-Scale Constraint-Based Metabolic Modelscited by 0
  32. 2026Evaluating Agentic Bioinformatics through Function, Evidence, and Validationcited by 0
  33. 2026HERMES: a multi-agent framework for structured knowledge extraction from ultra-long documents in geosciencecited by 0
  34. 2026One Score, Two Decisions: Selective Prediction on the Rare-Disease Tailcited by 0
  35. 2026An integrated diffusion-weighted imaging processing and interpretation platform for MR-guided radiotherapycited by 0
  36. 2026Learning to Fuse LLMs with Ontology Rankers for Rare-Disease Diagnosiscited by 0
  37. 2026Asclepius: An Adaptive Harness for Long-Horizon Clinical Agentscited by 0
  38. 2026HPOQuest: A Rare-Disease Diagnostic Agent Using Active Phenotype Acquisitioncited by 0

50 most cited of 52 All 52 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026RareLens: Towards End-to-End Rare Disease Care via Aligning Divergent Large Language Model Reasoning
  2. 2025A Specialized Large Language Model for Clinical Reasoning and Diagnosis in Rare Diseases
  3. 2026Teaching agentic AI to generalize expert diagnostic reasoning in rare diseases
  4. 2026DeepLens Diagnosis Agent: Agentic Workflow Design Lets a Small Reasoning Model Compete with Frontier LLMs
  5. 2026RareAlert: Aligning heterogeneous large language model reasoning for early rare disease risk screening
  6. 2025MEDDxAgent: A Unified Modular Agent Framework for Explainable Automatic Differential Diagnosis
  7. 2025Learning to reason about rare diseases through retrieval-augmented agents
  8. 2026Evaluating Multi-Agent LLM Architectures for Rare Disease Diagnosis