透過主動檢索的漸進式多模態推理

摘要

多步驟多模態推理任務對於多模態大型語言模型（MLLMs）構成重大挑戰，並且尋找有效方法以增強它們在這種情況下的表現仍然是一個未解決的問題。在本文中，我們提出了AR-MCTS，這是一個通用框架，旨在通過主動檢索（AR）和蒙特卡羅樹搜索（MCTS）逐步提升MLLMs的推理能力。我們的方法始於開發一個統一的檢索模塊，從混合模態檢索語料庫中檢索解決複雜推理問題所需的關鍵支持見解。為了彌補自動多模態推理驗證的差距，我們採用了結合主動檢索機制的MCTS算法，這使得可以自動生成逐步註釋。這種策略動態地為每個推理步驟檢索關鍵見解，超越了傳統的束搜索採樣，以改進推理空間的多樣性和可靠性。此外，我們引入了一個逐步對齊以支持自動驗證多模態推理任務的過程獎勵模型。在三個複雜多模態推理基準測試中的實驗結果證實了AR-MCTS框架在增強各種多模態模型表現方面的有效性。進一步的分析表明，AR-MCTS可以優化採樣多樣性和準確性，產生可靠的多模態推理。

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.

透過主動檢索的漸進式多模態推理

Progressive Multimodal Reasoning via Active Retrieval

摘要

Summary

Support