ReasonMed: A 370K Multi-Agent Generated Dataset for Advancing Medical Reasoning
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911199188221952 |
|---|---|
| author | Sun, Yu Qian, Xingyu Xu, Weiwen Zhang, Hao Xiao, Chenghao Li, Long Zhao, Deli Huang, Wenbing Xu, Tingyang Bai, Qifeng Rong, Yu |
| author_facet | Sun, Yu Qian, Xingyu Xu, Weiwen Zhang, Hao Xiao, Chenghao Li, Long Zhao, Deli Huang, Wenbing Xu, Tingyang Bai, Qifeng Rong, Yu |
| contents | Reasoning-based large language models have excelled in mathematics and programming, yet their potential in knowledge-intensive medical question answering remains underexplored and insufficiently validated in clinical contexts. To bridge this gap, we introduce ReasonMed, the largest medical reasoning dataset to date, comprising 370k high-quality examples distilled from 1.75 million initial reasoning paths generated by complementary LLMs and curated through a cost-efficient easy-medium-difficult (EMD) pipeline. ReasonMed is built through a multi-agent generation, verification, and refinement process, in which an Error Refiner improves reasoning paths by correcting error-prone steps identified by a verifier. Using ReasonMed, we investigate effective strategies for training medical reasoning models and find that integrating detailed CoT reasoning with concise answer summaries yields the most robust fine-tuning results. Models trained on ReasonMed set a new benchmark: ReasonMed-7B surpasses the prior best sub-10B models by 4.17% and even exceeds LLaMA3.1-70B on PubMedQA by 4.60%. When scaled to ReasonMed-14B, it remains highly competitive, underscoring consistent scaling potential. The codes and datasets are available at https://github.com/YuSun-Work/ReasonMed. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_09513 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ReasonMed: A 370K Multi-Agent Generated Dataset for Advancing Medical Reasoning Sun, Yu Qian, Xingyu Xu, Weiwen Zhang, Hao Xiao, Chenghao Li, Long Zhao, Deli Huang, Wenbing Xu, Tingyang Bai, Qifeng Rong, Yu Computation and Language Artificial Intelligence Multiagent Systems Reasoning-based large language models have excelled in mathematics and programming, yet their potential in knowledge-intensive medical question answering remains underexplored and insufficiently validated in clinical contexts. To bridge this gap, we introduce ReasonMed, the largest medical reasoning dataset to date, comprising 370k high-quality examples distilled from 1.75 million initial reasoning paths generated by complementary LLMs and curated through a cost-efficient easy-medium-difficult (EMD) pipeline. ReasonMed is built through a multi-agent generation, verification, and refinement process, in which an Error Refiner improves reasoning paths by correcting error-prone steps identified by a verifier. Using ReasonMed, we investigate effective strategies for training medical reasoning models and find that integrating detailed CoT reasoning with concise answer summaries yields the most robust fine-tuning results. Models trained on ReasonMed set a new benchmark: ReasonMed-7B surpasses the prior best sub-10B models by 4.17% and even exceeds LLaMA3.1-70B on PubMedQA by 4.60%. When scaled to ReasonMed-14B, it remains highly competitive, underscoring consistent scaling potential. The codes and datasets are available at https://github.com/YuSun-Work/ReasonMed. |
| title | ReasonMed: A 370K Multi-Agent Generated Dataset for Advancing Medical Reasoning |
| topic | Computation and Language Artificial Intelligence Multiagent Systems |
| url | https://arxiv.org/abs/2506.09513 |