# An Agentic System for Rare Disease Diagnosis with Traceable Reasoning

arXiv: https://arxiv.org/abs/2506.20430 · HTML: https://mlsanity.com/paper/2506.20430/

## 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.

## Placed in

- LLM reasoning / [Clinical and biomedical applications](https://mlsanity.com/lr/clinical-and-biomedical-applications/)
- LLM agents and tool use / [Medical and scientific domain agents](https://mlsanity.com/agents/medical-and-scientific-domain-agents/)

## Builds on (most cited first, 16 of 16)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agents](https://mlsanity.com/paper/2306.03314/) (2023)
- [MedCPT: Contrastive Pre-trained Transformers with Large-scale PubMed Search Logs for Zero-shot Biomedical Information Retrieval](https://mlsanity.com/paper/2307.00589/) (2023)
- [MDAgents: An Adaptive Collaboration of LLMs for Medical Decision-Making](https://mlsanity.com/paper/2404.15155/) (2024)
- [MME-CoT: Benchmarking Chain-of-Thought in Large Multimodal Models for Reasoning Quality, Robustness, and Efficiency](https://mlsanity.com/paper/2502.09621/) (2025)
- [Towards Accurate Differential Diagnosis with Large Language Models](https://mlsanity.com/paper/2312.00164/) (2023)
- [Evaluating GPT-4 and ChatGPT on Japanese Medical Licensing Examinations](https://mlsanity.com/paper/2303.18027/) (2023)
- [RareBench: Can LLMs Serve as Rare Diseases Specialists?](https://mlsanity.com/paper/2402.06341/) (2024)
- [Baichuan-M1: Pushing the Medical Capability of Large Language Models](https://mlsanity.com/paper/2502.12671/) (2025)
- [Towards Evaluating and Building Versatile Large Language Models for Medicine](https://mlsanity.com/paper/2408.12547/) (2024)
- [BioLORD: Learning Ontological Representations from Definitions (for Biomedical Concepts and their Textual Descriptions)](https://mlsanity.com/paper/2210.11892/) (2022)
- [PMC-Patients: A Large-scale Dataset of Patient Summaries and Relations for Benchmarking Retrieval-based Clinical Decision Support Systems](https://mlsanity.com/paper/2202.13876/) (2022)
- [How Well Can Modern LLMs Act as Agent Cores in Radiology Environments?](https://mlsanity.com/paper/2412.09529/) (2024)
- [RareAgents: Autonomous Multi-disciplinary Team for Rare Disease Diagnosis and Treatment](https://mlsanity.com/paper/2412.12475/) (2024)

## Built on by (most cited first, 30 of 52)

- [MedResearcher-R1: Expert-Level Medical Deep Researcher via A Knowledge-Informed Trajectory Synthesis Framework](https://mlsanity.com/paper/2508.14880/) (2025)
- [End-to-End Agentic RAG System Training for Traceable Diagnostic Reasoning](https://mlsanity.com/paper/2508.15746/) (2025)
- [Qworld: Question-Specific Evaluation Criteria for LLMs](https://mlsanity.com/paper/2603.23522/) (2026)
- [CXRAgent: Director-Orchestrated Multi-Stage Reasoning for Chest X-Ray Interpretation](https://mlsanity.com/paper/2510.21324/) (2025)
- [From Conflict to Consensus: Boosting Medical Reasoning via Multi-Round Agentic RAG](https://mlsanity.com/paper/2603.03292/) (2026)
- [Evo-MedAgent: Beyond One-Shot Diagnosis with Agents That Remember, Reflect, and Improve](https://mlsanity.com/paper/2604.14475/) (2026)
- [MedOpenClaw and MedFlowBench: Auditing Medical Agents in Full-Study Workflows](https://mlsanity.com/paper/2603.24649/) (2026)
- [End-to-end autonomous scientific discovery on a real optical platform](https://mlsanity.com/paper/2604.27092/) (2026)
- [QCAgent: An agentic framework for quality-controllable pathology report generation from whole slide image](https://mlsanity.com/paper/2603.01647/) (2026)
- [A Vision-Language Foundation Model for Zero-shot Clinical Collaboration and Automated Concept Discovery in Dermatology](https://mlsanity.com/paper/2602.10624/) (2026)
- [Joint Optimization of Reasoning and Dual-Memory for Self-Learning Diagnostic Agent](https://mlsanity.com/paper/2604.07269/) (2026)
- [Teaching large language models to reason like expert diagnosticians](https://mlsanity.com/paper/2509.12194/) (2025)
- [Rank-and-Reason: Multi-Agent Collaboration Accelerates Zero-Shot Protein Mutation Prediction](https://mlsanity.com/paper/2602.00197/) (2026)
- [Emulating Clinician Cognition via Self-Evolving Deep Clinical Research](https://mlsanity.com/paper/2603.10677/) (2026)
- [A Versatile AI Agent for Rare Disease Diagnosis and Risk Gene Prioritization](https://mlsanity.com/paper/2605.06226/) (2026)
- [An agentic framework for gravitational-wave counterpart association in the multi-messenger era](https://mlsanity.com/paper/2605.10584/) (2026)
- [LatentDx: Latent Multi-Agent Communication for Cross-Hospital Rare-Disease Diagnosis](https://mlsanity.com/paper/2606.13945/) (2026)
- [LA-MARRVEL: A Knowledge-Grounded, Language-Aware LLM Framework for Clinically Robust Rare Disease Gene Prioritization](https://mlsanity.com/paper/2511.02263/) (2025)
- [Colon-X: Advancing Intelligent Colonoscopy toward Clinical Reasoning](https://mlsanity.com/paper/2512.03667/) (2025)
- [Which Tool Response Should I Trust? Tool-Expertise-Aware Chest X-ray Agent with Multimodal Agentic Learning](https://mlsanity.com/paper/2602.21517/) (2026)
- [QuantClaw: Precision Where It Matters for OpenClaw](https://mlsanity.com/paper/2604.22577/) (2026)
- [KISS - Knowledge Infrastructure for Scientific Simulation: A Scaffolding for Agentic Earth Science](https://mlsanity.com/paper/2605.17856/) (2026)
- [DDX-TRACE: A Benchmark for Medical Diagnostic Trajectories in VLMs](https://mlsanity.com/paper/2605.23629/) (2026)
- [RDMA: Cost Effective Agent-Driven Rare Disease Mining from Electronic Health Records](https://mlsanity.com/paper/2507.15867/) (2025)
- [Adversarial Robustness in Zero-Shot Learning:An Empirical Study on Class and Concept-Level Vulnerabilities](https://mlsanity.com/paper/2512.18651/) (2025)
- [Multi-Agent Causal Reasoning System for Error Pattern Rule Automation in Vehicles](https://mlsanity.com/paper/2602.01155/) (2026)
- [OMGs: A multi-agent system supporting MDT decision-making across the ovarian tumour care continuum](https://mlsanity.com/paper/2602.13793/) (2026)
- [An artificial intelligence framework for end-to-end rare disease phenotyping from clinical notes using large language models](https://mlsanity.com/paper/2602.20324/) (2026)
- [FetalAgents: A Multi-Agent System for Fetal Ultrasound Image and Video Analysis](https://mlsanity.com/paper/2603.09733/) (2026)
- [Cerebra: A Multidisciplinary AI Board for Multimodal Dementia Characterization and Risk Assessment](https://mlsanity.com/paper/2603.21597/) (2026)

## 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.