Tag
This technical report presents the 1st-place solution for the SeePhys Pro challenge at ICML 2026's AI4Math Workshop, using a two-stage framework with visual information extraction and multi-agent debate to answer college-level physics questions from images.
This position paper reviews the current state of LLM-driven formal mathematics, identifies key limitations in applying these systems to open-ended research mathematics, and proposes a strategic roadmap for developing AI agents capable of advancing mathematical frontiers.
Discussed the current state and future of AI in mathematics. Citing an example, ChatGPT 5.5 Pro autonomously solved the farthest pair problem in high-dimensional computational geometry, which had been stuck for years, demonstrating AI's potential in mathematical discovery.