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

Qi Yang, Chenghao Zhang, Lubin Fan, Kun Ding, Jieping Ye and Shiming Xiang

This repository provides the PyTorch implementation for the paper "Re-ranking Reasoning Context with Tree Search Makes Large Vision-Language Models Stronger" accepted by ICML 2025 (Spotlight).

🔥What's New

• (2025. 5.1) Our paper (RCTS) is accepted as ICML Spotlight Paper! 😮 (Happy Labor Day! 👷👷‍♀️)

🪵 TODO List

• Update the Code! (Coming Soon!) (Before this month!)
• Completed the README.md. (Before 6.15!)
• Release the paper on arxiv.

📚Method

TODO

🛠️ Getting Started

TODO

🤝 Citing RCTS

@misc{yang2025rerankingreasoningcontexttree,
      title={Re-ranking Reasoning Context with Tree Search Makes Large Vision-Language Models Stronger}, 
      author={Qi Yang and Chenghao Zhang and Lubin Fan and Kun Ding and Jieping Ye and Shiming Xiang},
      year={2025},
      eprint={2506.07785},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2506.07785}, 
}