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

Qi Yang, Chenghao Zhang, Lubin Fan, Kun Ding, Jieping Ye, Shiming Xiang
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:71521-71542, 2025.

Abstract

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-yang25at, title = {Re-ranking Reasoning Context with Tree Search Makes Large Vision-Language Models Stronger}, author = {Yang, Qi and Zhang, Chenghao and Fan, Lubin and Ding, Kun and Ye, Jieping and Xiang, Shiming}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {71521--71542}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/yang25at/yang25at.pdf}, url = {https://proceedings.mlr.press/v267/yang25at.html}, abstract = {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.} }
Endnote
%0 Conference Paper %T Re-ranking Reasoning Context with Tree Search Makes Large Vision-Language Models Stronger %A Qi Yang %A Chenghao Zhang %A Lubin Fan %A Kun Ding %A Jieping Ye %A Shiming Xiang %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-yang25at %I PMLR %P 71521--71542 %U https://proceedings.mlr.press/v267/yang25at.html %V 267 %X 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.
APA
Yang, Q., Zhang, C., Fan, L., Ding, K., Ye, J. & Xiang, S.. (2025). Re-ranking Reasoning Context with Tree Search Makes Large Vision-Language Models Stronger. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:71521-71542 Available from https://proceedings.mlr.press/v267/yang25at.html.

Related Material