Breaking Failure Cascades: Step-Aware Reinforcement Learning for Medical Multimodal Reasoning
For medical multimodal LLMs, MRPO addresses the critical problem of cascading reasoning errors in outcome-centric training, offering a targeted solution to improve reasoning quality and accuracy.
The paper introduces MRPO, a reinforcement learning algorithm with step-wise process rewards that penalizes early reasoning errors exponentially, reducing cascading failures in medical VQA. On Qwen3-VL-8B-Instruct, MRPO surpasses HuatuoGPT-Vision-34B by 2.79 points and cuts early-stage reasoning failures from 64.0% to 13.0%.
Recent multimodal large language models have shown great promise in clinical image reasoning, but existing post-training pipelines remain predominantly outcome-centric, relying on final answer correctness or sequence-level preferences. This suffers from sparse credit assignment, making it difficult to optimize the reasoning process essential for clinical applications. Our analysis reveals that cascading errors from early-stage reasoning failures are a leading cause of incorrect predictions in medical visual question answering (VQA) benchmarks. Motivated by this, we propose Medical Reasoning-aware Policy Optimization (MRPO), an RL algorithm that incorporates step-wise process rewards. When the final answer is incorrect, MRPO assigns exponentially larger penalties to tokens in earlier invalid reasoning steps, breaking failure cascades without compromising successful paths. Across three multimodal LLM backbones, MRPO consistently outperforms standard GRPO and a recent RL baseline, and on Qwen3-VL-8B-Instruct even surpasses substantially larger medical MLLMs such as HuatuoGPT-Vision-34B by 2.79 points. Moreover, MRPO reduces early-stage reasoning failures from 64.0% to 13.0%, showing that targeted mitigation of cascading failures improves both reasoning quality and final answer accuracy. Our code is available at https://github.com/dmis-lab/MRPO