Self-consistency methods are the core technique for improving the reasoning reliability of multimodal large language models (MLLMs). By generating multiple reasoning results through repeated sampling and selecting the best answer via voting, they play an important role in cross-modal tasks. However, most existing self-consistency methods are limited to a fixed ``repeated sampling and voting'' paradigm and do not reuse historical reasoning information. As a result, models struggle to actively correct visual understanding errors and dynamically adjust their reasoning during iteration. Inspired by the human reasoning behavior of repeated verification and dynamic error correction, we propose the H-GIVR framework. During iterative reasoning, the MLLM observes the image multiple times and uses previously generated answers as references for subsequent steps, enabling dynamic correction of errors and improving answer accuracy. We conduct comprehensive experiments on five datasets and three models. The results show that the H-GIVR framework can significantly improve cross-modal reasoning accuracy while maintaining low computational cost. For instance, using \texttt{Llama3.2-vision:11b} on the ScienceQA dataset, the model requires an average of 2.57 responses per question to achieve an accuracy of 78.90\%, representing a 107\% improvement over the baseline.

翻译：自一致性方法是提升多模态大语言模型（MLLMs）推理可靠性的核心技术。通过重复采样生成多个推理结果，并经由投票选出最佳答案，它们在跨模态任务中扮演着重要角色。然而，现有的大多数自一致性方法局限于固定的“重复采样与投票”范式，未能复用历史推理信息。这导致模型难以主动修正视觉理解错误，并在迭代过程中动态调整其推理。受人类反复验证与动态纠错的推理行为启发，我们提出了H-GIVR框架。在迭代推理过程中，MLLM多次观察图像，并将先前生成的答案作为后续步骤的参考，从而实现错误的动态校正并提升答案准确性。我们在五个数据集和三个模型上进行了全面实验。结果表明，H-GIVR框架能在保持较低计算成本的同时，显著提升跨模态推理的准确率。例如，在ScienceQA数据集上使用 \texttt{Llama3.2-vision:11b} 模型时，平均每个问题仅需2.57次响应即可达到78.90\%的准确率，相比基线提升了107\%。