Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a prevailing paradigm for enhancing reasoning in Multimodal Large Language Models (MLLMs). However, relying solely on outcome supervision risks reward hacking, where models learn spurious reasoning patterns to satisfy final answer checks. While recent rubric-based approaches offer fine-grained supervision signals, they suffer from high computational costs of instance-level generation and inefficient training dynamics caused by treating all rubrics as equally learnable. In this paper, we propose Stratified Rubric-based Curriculum Learning (RuCL), a novel framework that reformulates curriculum learning by shifting the focus from data selection to reward design. RuCL generates generalized rubrics for broad applicability and stratifies them based on the model's competence. By dynamically adjusting rubric weights during training, RuCL guides the model from mastering foundational perception to tackling advanced logical reasoning. Extensive experiments on various visual reasoning benchmarks show that RuCL yields a remarkable +7.83% average improvement over the Qwen2.5-VL-7B model, achieving a state-of-the-art accuracy of 60.06%.
@article{arxiv.2602.21628,
title = {RuCL: Stratified Rubric-Based Curriculum Learning for Multimodal Large Language Model Reasoning},
author = {Yukun Chen and Jiaming Li and Longze Chen and Ze Gong and Jingpeng Li and Zhen Qin and Hengyu Chang and Ancheng Xu and Zhihao Yang and Hamid Alinejad-Rokny and Qiang Qu and Bo Zheng and Min Yang},
journal= {arXiv preprint arXiv:2602.21628},
year = {2026}
}