通过主动检索实现渐进式多模态推理

摘要

多步骤多模态推理任务对多模态大型语言模型（MLLMs）提出了重大挑战，在这种情况下如何提高其性能仍然是一个未解决的问题。在本文中，我们提出了AR-MCTS，这是一个通用框架，旨在通过主动检索（AR）和蒙特卡洛树搜索（MCTS）逐步提高MLLMs的推理能力。我们的方法始于开发一个统一的检索模块，从混合模态检索语料库中检索解决复杂推理问题的关键支持见解。为了弥合自动多模态推理验证中的差距，我们采用了MCTS算法结合主动检索机制，这使得能够自动生成逐步注释。该策略动态地为每个推理步骤检索关键见解，超越传统的波束搜索采样，以提高推理空间的多样性和可靠性。此外，我们引入了一个过程奖励模型，逐步与支持自动验证多模态推理任务相一致。在三个复杂的多模态推理基准测试中的实验结果证实了AR-MCTS框架在提高各种多模态模型性能方面的有效性。进一步的分析表明，AR-MCTS可以优化采样多样性和准确性，产生可靠的多模态推理。

English

Multi-step multimodal reasoning tasks pose significant challenges for multimodal large language models (MLLMs), and finding effective ways to enhance their performance in such scenarios remains an unresolved issue. In this paper, we propose AR-MCTS, a universal framework designed to progressively improve the reasoning capabilities of MLLMs through Active Retrieval (AR) and Monte Carlo Tree Search (MCTS). Our approach begins with the development of a unified retrieval module that retrieves key supporting insights for solving complex reasoning problems from a hybrid-modal retrieval corpus. To bridge the gap in automated multimodal reasoning verification, we employ the MCTS algorithm combined with an active retrieval mechanism, which enables the automatic generation of step-wise annotations. This strategy dynamically retrieves key insights for each reasoning step, moving beyond traditional beam search sampling to improve the diversity and reliability of the reasoning space. Additionally, we introduce a process reward model that aligns progressively to support the automatic verification of multimodal reasoning tasks. Experimental results across three complex multimodal reasoning benchmarks confirm the effectiveness of the AR-MCTS framework in enhancing the performance of various multimodal models. Further analysis demonstrates that AR-MCTS can optimize sampling diversity and accuracy, yielding reliable multimodal reasoning.

通过主动检索实现渐进式多模态推理

Progressive Multimodal Reasoning via Active Retrieval

摘要

Summary

Support