Enhancing the Outcome Reward-based RLTraining of MLLMs with Self-Consistency Sampling

Outcome-reward reinforcement learning (RL) is a common--and increasingly significant--way to refine the step-by-step reasoning of multimodal large language models (MLLMs). In the multiple-choice setting--a dominant format for multimodal reasoning benchmarks--the paradigm faces a significant yet often overlooked obstacle: unfaithful trajectories that guess the correct option after a faulty chain of thought receive the same reward as genuine reasoning, which is a flaw that cannot be ignored. We propose Self-Consistency Sampling (SCS) to correct this issue. For each question, SCS (i) introduces small visual perturbations and (ii) performs repeated truncation-and-resampling of an initial trajectory; agreement among the resulting trajectories yields a differentiable consistency score that down-weights unreliable traces during policy updates.