BiNSGPS: Geometry Problem Solving via Bidirectional Neuro-Symbolic Interaction

ArXi:2606.04648v1 Announce Type: new Geometry problem solving poses distinct challenges in artificial intelligence. Existing approaches typically fall into two paradigms: symbolic methods, which exhibit limited adaptability, and neural methods, which are prone to hallucinations. Recent neuro-symbolic hybrids predominantly rely on a unidirectional pipeline where neural outputs are fed into solvers without feedback, making system brittle to early-stage errors.