📄 论文总结
多模态科学推理：ICML 2025 SeePhys挑战赛技术报告与冠军方案 / Multimodal Reasoning for Science: Technical Report and 1st Place Solution to the ICML 2025 SeePhys Challenge
1️⃣ 一句话总结
这项研究提出了一种结合图像描述辅助的推理方法，有效解决了AI在多模态场景下的理解难题，并在科学推理竞赛中夺冠，同时验证了其在几何问题上的广泛适用性。
🤖 系统
Abstract - Multimodal Reasoning for Science: Technical Report and 1st Place Solution to the ICML 2025 SeePhys Challenge
Multimodal reasoning remains a fundamental challenge in artificial intelligence. Despite substantial advances in text-based reasoning, even state-of-the-art models such as GPT-o3 struggle to maintain strong performance in multimodal scenarios. To address this gap, we introduce a caption-assisted reasoning framework that effectively bridges visual and textual modalities. Our approach achieved 1st place in the ICML 2025 AI for Math Workshop \& Challenge 2: SeePhys, highlighting its effectiveness and robustness. Furthermore, we validate its generalization on the MathVerse benchmark for geometric reasoning, demonstrating the versatility of our method. Our code is publicly available at this https URL.