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.
LANS : A Layout-Aware Neural Solver for Plane Geometry Problem
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.AI 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
BiNSGPS proposes bidirectional neuro-symbolic interaction where an MLLM adviser uses symbolic solver feedback to rectify formal representations and propose hypotheses for geometry problem solving.
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.
-
BiNSGPS: Geometry Problem Solving via Bidirectional Neuro-Symbolic Interaction
BiNSGPS proposes bidirectional neuro-symbolic interaction where an MLLM adviser uses symbolic solver feedback to rectify formal representations and propose hypotheses for geometry problem solving.