RareDxR1: Autonomous Medical Reasoning for Rare Disease Diagnosis Beyond Human Annotation
Quick Answer
RareDxR1 is a novel end-to-end large language model for rare disease diagnosis, achieving state-of-the-art accuracy without human annotation.
Quick Take
It utilizes Reflection-Enhanced Reasoning Sampling (RERS) and dual-level curriculum reinforcement learning, significantly improving diagnostic reasoning from unstructured clinical notes.
Key Points
- Introduces RareDxR1, an AI model for open-domain rare disease diagnosis.
- Employs Reflection-Enhanced Reasoning Sampling to synthesize expert diagnostic paths.
- Achieves state-of-the-art accuracy across various benchmarks.
- Utilizes dual-level curriculum reinforcement learning for improved training.
- Code and dataset will be publicly available for further research.
Paper Resources
📖 Reader Mode
~2 min readAbstract:Rare disease differential diagnosis is a critical yet arduous clinical task, requiring physicians to identify precise phenotypes from complex, unstructured patient symptoms and execute intricate reasoning within a vast search space. However, existing AI approaches typically rely on pipeline-based phenotype extraction or retrieval-augmented generation, which suffer from critical information loss due to predefined ontologies, retrieval bottlenecks, and a lack of diagnostic logic. To address these challenges, we introduce RareDxR1, an end-to-end reasoning-centric large language model designed for open-domain rare disease diagnosis directly from unstructured clinical notes. We design a progressive end-to-end training framework by synergizing knowledge internalization with autonomous evolutionary learning, thereby bypassing reliance on structured phenotypes and closed-set decision-making. To overcome the limitations of RAG and phenotype restriction, we enabled the deep internalization of fragmented rare-disease knowledge directly into the model's parameters. Moreover, to bridge the gap between model generation and expert reasoning, we propose Reflection-Enhanced Reasoning Sampling (RERS), a strategy that synthesizes expert-level diagnostic trajectories by learning from failures without human annotation. Additionally, we propose a dual-level curriculum reinforcement learning approach for gradually mastering rare disease diagnosis. Experimental results demonstrate that RareDxR1 achieves state-of-the-art accuracy across different benchmarks, marking a significant breakthrough in open-domain rare disease diagnosis. Our code and dataset will be publicly available.
| Comments: | 7 pages, 3 figures. Accepted to IEEE International Conference on Multimedia and Expo (ICME) 2026 |
| Subjects: | Artificial Intelligence (cs.AI) |
| ACM classes: | I.2.7; I.2.6; J.3 |
| Cite as: | arXiv:2607.00147 [cs.AI] |
| (or arXiv:2607.00147v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2607.00147 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Deyang Jiang [view email]
[v1]
Tue, 30 Jun 2026 20:25:53 UTC (1,143 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →HOBA: Hierarchical On-Policy Bidding Agents for Adaptive Online Advertising
HOBA (Hierarchical On-policy Bidding Agents) is a novel hierarchical reinforcement learning framework that enhances online advertising bidding systems by improving adaptability and reducing hyperparameter tuning costs. It utilizes a for hyperparameter inference, a SARSA agent for expert model selection, and a dynamic expert pool for bid execution, achieving a +3.6% increase in target cost during large-scale deployment and outperforming state-of-the-art baselines on AuctionNet.