← Back ◬ AI & Machine Learning Jun 04, 2026

BiNSGPS: Geometry Problem Solving via Bidirectional Neuro-Symbolic Interaction

arXiv AI Archived Jun 04, 2026 ✓ Full text saved

arXiv:2606.04648v1 Announce Type: new 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 unidirection

Full text archived locally

✦ AI Summary · Claude Sonnet

Computer Science > Artificial Intelligence [Submitted on 3 Jun 2026] BiNSGPS: Geometry Problem Solving via Bidirectional Neuro-Symbolic Interaction Qi Wang, Peijie Wang, Fei Yin, Cheng-Lin Liu 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. Subjects: Artificial Intelligence (cs.AI) Cite as: arXiv:2606.04648 [cs.AI] (or arXiv:2606.04648v1 [cs.AI] for this version) https://doi.org/10.48550/arXiv.2606.04648 Focus to learn more Submission history From: Wang Peijie [view email] [v1] Wed, 3 Jun 2026 09:18:37 UTC (2,624 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev | next > new | recent | 2026-06 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

💬 Team Notes