{"ID":3050145,"CreatedAt":"2026-06-04T02:13:16.786527022Z","UpdatedAt":"2026-06-06T08:58:50.400332682Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.04648","arxiv_id":"2606.04648","title":"BiNSGPS: Geometry Problem Solving via Bidirectional Neuro-Symbolic Interaction","abstract":"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. To break this unidirectional bottleneck, we propose BiNSGPS, a framework that establishes Bidirectional Neuro-Symbolic Interaction (BiNS) between a MLLM Adviser and a Symbolic Solver. MLLM Adviser actively incorporates feedback from the symbolic solver to dynamically rectify inconsistent formal representations or propose auxiliary hypotheses, resolving symbolic conflicts and facilitating complex deductions.","short_abstract":"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...","url_abs":"https://arxiv.org/abs/2606.04648","url_pdf":"https://arxiv.org/pdf/2606.04648v1","authors":"[\"Qi Wang\",\"Peijie Wang\",\"Fei Yin\",\"Cheng-Lin Liu\"]","published":"2026-06-03T09:18:37Z","proceeding":"cs.AI","tasks":"[\"cs.AI\"]","methods":"[\"Large Language Model\"]","has_code":false}