Multimodal large language models (MLLMs) have rapidly advanced from perception tasks to complex multi-step reasoning, yet reinforcement learning with verifiable rewards (RLVR) often leads to spurious reasoning since only the final-answer correctness is rewarded. To address this limitation, we propose AutoRubric, a framework that integrates RLVR with process-level supervision through automatically collected rubric-based generative rewards. Our key innovation lies in a scalable self-aggregation method that distills consistent reasoning checkpoints from successful trajectories, enabling problem-specific rubric construction without human annotation or stronger teacher models. By jointly leveraging rubric-based and outcome rewards, AutoRubric achieves state-of-the-art performance on six multimodal reasoning benchmarks and substantially improves reasoning faithfulness in dedicated evaluations.
@article{arxiv.2510.14738,
title = {AutoRubric: Rubric-Based Generative Rewards for Faithful Multimodal Reasoning},
author = {Mengzhao Jia and Zhihan Zhang and Ignacio Cases and Zheyuan Liu and Meng Jiang and Peng Qi},
journal= {arXiv preprint arXiv:2510.14738},
year = {2026}
}