Re-ranking Reasoning Context with Tree Search Makes Large Vision-Language Models Stronger

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yang, Qi, Zhang, Chenghao, Fan, Lubin, Ding, Kun, Ye, Jieping, Xiang, Shiming
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915333589172224
author Yang, Qi
Zhang, Chenghao
Fan, Lubin
Ding, Kun
Ye, Jieping
Xiang, Shiming
author_facet Yang, Qi
Zhang, Chenghao
Fan, Lubin
Ding, Kun
Ye, Jieping
Xiang, Shiming
contents Recent advancements in Large Vision Language Models (LVLMs) have significantly improved performance in Visual Question Answering (VQA) tasks through multimodal Retrieval-Augmented Generation (RAG). However, existing methods still face challenges, such as the scarcity of knowledge with reasoning examples and erratic responses from retrieved knowledge. To address these issues, in this study, we propose a multimodal RAG framework, termed RCTS, which enhances LVLMs by constructing a Reasoning Context-enriched knowledge base and a Tree Search re-ranking method. Specifically, we introduce a self-consistent evaluation mechanism to enrich the knowledge base with intrinsic reasoning patterns. We further propose a Monte Carlo Tree Search with Heuristic Rewards (MCTS-HR) to prioritize the most relevant examples. This ensures that LVLMs can leverage high-quality contextual reasoning for better and more consistent responses. Extensive experiments demonstrate that our framework achieves state-of-the-art performance on multiple VQA datasets, significantly outperforming In-Context Learning (ICL) and Vanilla-RAG methods. It highlights the effectiveness of our knowledge base and re-ranking method in improving LVLMs. Our code is available at https://github.com/yannqi/RCTS-RAG.
format Preprint
id arxiv_https___arxiv_org_abs_2506_07785
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Re-ranking Reasoning Context with Tree Search Makes Large Vision-Language Models Stronger
Yang, Qi
Zhang, Chenghao
Fan, Lubin
Ding, Kun
Ye, Jieping
Xiang, Shiming
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Recent advancements in Large Vision Language Models (LVLMs) have significantly improved performance in Visual Question Answering (VQA) tasks through multimodal Retrieval-Augmented Generation (RAG). However, existing methods still face challenges, such as the scarcity of knowledge with reasoning examples and erratic responses from retrieved knowledge. To address these issues, in this study, we propose a multimodal RAG framework, termed RCTS, which enhances LVLMs by constructing a Reasoning Context-enriched knowledge base and a Tree Search re-ranking method. Specifically, we introduce a self-consistent evaluation mechanism to enrich the knowledge base with intrinsic reasoning patterns. We further propose a Monte Carlo Tree Search with Heuristic Rewards (MCTS-HR) to prioritize the most relevant examples. This ensures that LVLMs can leverage high-quality contextual reasoning for better and more consistent responses. Extensive experiments demonstrate that our framework achieves state-of-the-art performance on multiple VQA datasets, significantly outperforming In-Context Learning (ICL) and Vanilla-RAG methods. It highlights the effectiveness of our knowledge base and re-ranking method in improving LVLMs. Our code is available at https://github.com/yannqi/RCTS-RAG.
title Re-ranking Reasoning Context with Tree Search Makes Large Vision-Language Models Stronger
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2506.07785