Metraipolis › archive › dc_e6ddca81f625
From Symbolic Perception to Logical Deduction: A Framework for Guiding Language Models in Geometric Reasoning — arXiv:2609.10335
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.10335
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T07:24:45.122Z
- SHA-256 of the archived text
6d959ba98ca1d28ee3189338e2a9255b6ccf56ca6b1e5a2507c339550537be1e- Stable URL of this page
https://metraipolis.com/documento/dc_e6ddca81f625
How to cite
From Symbolic Perception to Logical Deduction: A Framework for Guiding Language Models in Geometric Reasoning — arXiv:2609.10335 — arXiv (en), https://arxiv.org/abs/2609.10335 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e6ddca81f625 (Metraipolis archive dc_e6ddca81f625, sha256 6d959ba98ca1d28ee3189338e2a9255b6ccf56ca6b1e5a2507c339550537be1e)
BibTeX
@misc{dce6ddca81f625,
title = {From Symbolic Perception to Logical Deduction: A Framework for Guiding Language Models in Geometric Reasoning — arXiv:2609.10335},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.10335},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e6ddca81f625; sha256 6d959ba98ca1d28ee3189338e2a9255b6ccf56ca6b1e5a2507c339550537be1e},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.10335. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Plane geometry remains a significant challenge in AI, requiring the integration of visual perception and mathematical reasoning. While Large Multimodal Models (LMMs) naturally handle visuo-linguistic inputs, they are often computationally intensive and opaque. We demonstrate that a pure Large Language Model (LLM), when equipped with specialized modules, can rival state-of-the-art LMMs on complex geometry problems. Our framework integrates a Geometric Vision Parser, which translates diagrams into symbolic form, with a Symbolic Solver that performs formal deductions, thereby mitigating hallucinations and promoting interpretable reasoning. To enable rigorous evaluation, we curate a benchmark of challenging problems from the 2025 Chinese Zhongkao examinations, ensuring data novelty and testing deeper deductive skills. Experiments demonstrate that our approach achieves performance comparable to Gemini 2.5 Pro while delivering clearer, human-like solutions. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-10 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2609.10335 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-16T07:00:16.251Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-10?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).