SD-GPS uses solver-driven autoformalization via QwenVL3-2B with RL on executability and an impasse-aware verified theorem proposer to outperform prior methods on Geometry3K and PGPS9K.
FGeo- HyperGNet: Geometric Problem Solving Integrating Formal Symbolic System and Hy- pergraph Neural Network
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
AI for math combines task-specific architectures and general foundation models to support research and advance AI reasoning capabilities.
citing papers explorer
-
Verifiable Geometry Problem Solving: Solver-Driven Autoformalization and Theorem Proposing
SD-GPS uses solver-driven autoformalization via QwenVL3-2B with RL on executability and an impasse-aware verified theorem proposer to outperform prior methods on Geometry3K and PGPS9K.
-
AI for Mathematics: Progress, Challenges, and Prospects
AI for math combines task-specific architectures and general foundation models to support research and advance AI reasoning capabilities.