几何推理框架：从符号感知到逻辑演绎
From Symbolic Perception to Logical Deduction: A Framework for Guiding Language Models in Geometric Reasoning
清华团队发布几何推理框架，用LLM+专用模块解决几何题，性能比肩Gemini 2.5 Pro，解题过程更清晰。
研究团队开发了一种纯大语言模型框架，通过几何视觉解析器和符号求解器模块，解决平面几何问题。该框架在2025年中国中考难题基准测试中表现与Gemini 2.5 Pro相当，同时提供更清晰类人的解决方案。研究表明，配备专门模块的LLM可媲美最先进的多模态模型，同时减少幻觉并提高推理可解释性。
From Symbolic Perception to Logical Deduction: A Framework for Guiding Language Models in Geometric Reasoning
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.