EMNLP 2026 Main · 2026 · Accepted
Breaking Failure Cascades: Step-Aware Reinforcement Learning for Medical Multimodal Reasoning
Step-aware reinforcement learning reduces cascading errors in medical multimodal reasoning.
Paper
Abstract
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 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. Moreover, MRPO reduces early-stage reasoning failures from 58.6% to 13.4%, 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
Source: arXiv:2606.31825. Version dated .
Resources
Read and cite this paper
@inproceedings{mrpo2026,
title = {Breaking Failure Cascades: Step-Aware Reinforcement Learning for Medical Multimodal Reasoning},
author = {Jung, Junha and Jeong, Minbyul and Lim, Suhyeon and Jung, Sungwook and Yun, Jaehoon and Roh, Taeyun and Sung, Mujeen and Kang, Jaewoo},
year = {2026},
booktitle = {EMNLP 2026 Main},
eprint = {2606.31825},
archivePrefix = {arXiv},
doi = {10.48550/arXiv.2606.31825},
url = {https://arxiv.org/abs/2606.31825}
}