#artificial intelligence
Jun 2026
Breaking Failure Cascades: Step-Aware Reinforcement Learning for Medical Multimodal Reasoning
Across four multimodal LLM backbones, MRPO consistently outperforms standard GRPO and a recent RL baseline, and on Qwen3-VL-8B-Thinking even surpasses substantially larger medical MLLMs such as HuatuoGPT-Vision-34B by 4.59 points.
Jun-Ha Jung, Minbyul Jeong, Suhyeon Lim et al.
· arXiv.org · 2 citations