{"type":"rich","version":"1.0","provider_name":"Transistor","provider_url":"https://transistor.fm","author_name":"Daily Paper Cast","title":"ReasonMed: A 370K Multi-Agent Generated Dataset for Advancing Medical Reasoning","html":"","width":"100%","height":180,"duration":1314,"description":"\n 🤗 Upvotes: 63 | cs.CL, cs.AI, cs.MA\n\n Authors:\n Yu Sun, Xingyu Qian, Weiwen Xu, Hao Zhang, Chenghao Xiao, Long Li, Yu Rong, Wenbing Huang, Qifeng Bai, Tingyang Xu\n\n Title:\n ReasonMed: A 370K Multi-Agent Generated Dataset for Advancing Medical Reasoning\n\n Arxiv:\n http://arxiv.org/abs/2506.09513v1\n\n Abstract:\n Though reasoning-based large language models (LLMs) have excelled in mathematics and programming, their capabilities in knowledge-intensive medical question answering remain underexplored. To address this, we introduce ReasonMed, the largest medical reasoning dataset, comprising 370k high-quality examples distilled from 1.7 million initial reasoning paths generated by various LLMs. ReasonMed is constructed through a \\textit{multi-agent verification and refinement process}, where we design an \\textit{Error Refiner} to enhance the reasoning paths by identifying and correcting error-prone steps flagged by a verifier. Leveraging ReasonMed, we systematically investigate best practices for training medical reasoning models and find that combining detailed Chain-of-Thought (CoT) reasoning with concise answer summaries yields the most effective fine-tuning strategy. Based on this strategy, we train ReasonMed-7B, which sets a new benchmark for sub-10B models, outperforming the prior best by 4.17\\% and even exceeding LLaMA3.1-70B on PubMedQA by 4.60\\%.\n ","thumbnail_url":"https://img.transistorcdn.com/8lOVNnuwhrA3rxrDMv7Osu4j_t1-jORooO6NfGcQhcw/rs:fill:0:0:1/w:400/h:400/q:60/mb:500000/aHR0cHM6Ly9pbWct/dXBsb2FkLXByb2R1/Y3Rpb24udHJhbnNp/c3Rvci5mbS81Zjg1/YzRhODczMDU4MmE4/OGMwN2FiNDlmYzI2/MDliMi5qcGVn.webp","thumbnail_width":300,"thumbnail_height":300}