Large Language Models (LLMs) demonstrate ever-increasing abilities in mathematical and algorithmic tasks, yet their geometric reasoning skills are underexplored. We investigate LLMs' abilities in constructive geometric problem-solving one of the most fundamental steps in the development of human mathematical reasoning. Our work reveals notable challenges that the state-of-the-art LLMs face in this domain despite many successes in similar areas. LLMs exhibit biases in target variable selection and struggle with 2D spatial relationships, often misrepresenting and hallucinating objects and their placements. To this end, we introduce a framework that formulates an LLMs-based multi-agents system that enhances their existing reasoning potential by conducting an internal dialogue. This work underscores LLMs' current limitations in geometric reasoning and improves geometric reasoning capabilities through self-correction, collaboration, and diverse role specializations.

大型语言模型（LLMs）在数学和算法任务中展现日益增长的能力，但它们的几何推理技能尚未被充分探索。我们研究了LLMs在构造性几何问题求解上的能力，这是人类数学推理发展中最基本的一步。我们的工作揭示了当前LLMs面临的显著挑战，尽管在类似领域取得了很多成功。LLMs在目标变量选择上存在偏见，并且在二维空间关系方面遇到困难，常常误代和产生对象及其放置的幻觉。为此，我们介绍了一个基于LLMs的多智能体系统框架，通过进行内部对话来增强它们现有的推理潜力。这项工作突出了LLMs在几何推理中目前的局限性，并通过自我纠正、协作和多样化角色专业化来改善几何推理能力。

超越线和圆：揭示大型语言模型中的几何推理差距