RuCL: Stratified Rubric-Based Curriculum Learning for Multimodal Large Language Model Reasoning

Yukun Chen, Jiaming Li, Longze Chen, Ze Gong, Jingpeng Li, Zhen Qin, Hengyu Chang, Ancheng Xu, Zhihao Yang, Hamid Alinejad-Rokny, Qiang Qu, Bo Zheng, Min Yang · Feb 25, 2026 · Citations: 0

Automatic Metrics General Rubric Rating

Open arXiv RSS feed

Abstract

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%.

Human Data Lens

Uses human feedback: Yes
Feedback types: Rubric Rating
Rater population: Unknown
Unit of annotation: Multi Dim Rubric
Expertise required: General

Evaluation Lens

Evaluation modes: Automatic Metrics
Agentic eval: None
Quality controls: Not reported
Confidence: 0.70
Flags: None

Research Summary

Contribution Summary

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.

Why It Matters For Eval

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%.