Research Papers 论文研究 2d ago Updated 1d ago 更新于 1天前 46

Solving Is Not Drawing: A Benchmark for Diagrammatic Reasoning in Olympiad Geometry 解题不等于绘图:奥林匹克几何中的图解推理基准

Introduces a new open-source benchmark isolating diagrammatic reasoning as a distinct capability from mathematical problem-solving in olympiad geometry The benchmark comprises 954 self-contained geometry problems (297 hard subset), each paired with a solution and a human-authored, high-fidelity diagram in renderable Asymptote code A multi-modal evaluation suite includes text-, code-, image-, VLM-, and constraint-based metrics to assess diagram construction fidelity Current foundation models exhi 提出首个专门评估"图解推理"(diagrammatic reasoning)能力的奥林匹克几何基准测试,填补现有基准仅测量答案正确率的空白 数据集包含954个自包含奥林匹克几何问题(其中297个难题),每个问题配有解决方案和人工编写的高保真Asymptote代码图 当前基础模型在解题与画图之间存在显著能力鸿沟,平均编译成功率仅36.14% 研究发现强数学推理能力并不等同于准确构建几何图形的能力

62
Hot 热度
72
Quality 质量
65
Impact 影响力

Analysis 深度分析

TL;DR

  • Introduces a new open-source benchmark isolating diagrammatic reasoning as a distinct capability from mathematical problem-solving in olympiad geometry
  • The benchmark comprises 954 self-contained geometry problems (297 hard subset), each paired with a solution and a human-authored, high-fidelity diagram in renderable Asymptote code
  • A multi-modal evaluation suite includes text-, code-, image-, VLM-, and constraint-based metrics to assess diagram construction fidelity
  • Current foundation models exhibit a pronounced solving-vs-drawing gap, achieving only a 36.14% average compile success rate on diagram generation
  • Strong mathematical reasoning ability does not imply the ability to construct accurate geometric diagrams, revealing an unmeasured capability gap

Why It Matters

This benchmark addresses a critical blind spot in AI evaluation: while models like GPT and Claude excel at olympiad-level math, their ability to produce faithful geometric diagrams remains unmeasured and likely weak. For AI practitioners building systems that require spatial reasoning or multi-modal output, this work provides both a diagnostic tool and a clear target for improvement. The finding that mathematical reasoning and diagram construction are dissociable capabilities challenges the assumption that progress on one implies progress on the other.

Technical Details

  • Dataset: 954 self-contained olympiad geometry problems with a 297-problem hard subset, each accompanied by a human-authored solution and a high-fidelity diagram encoded in renderable Asymptote code
  • Evaluation Metrics: A multi-dimensional metric suite spanning text-based correctness, code-level compilation success, image fidelity, VLM-based assessment, and geometric constraint satisfaction
  • Key Finding: Foundation models achieve an average compile success rate of only 36.14% on diagram generation, demonstrating a significant gap between symbolic reasoning and visual-spatial construction
  • Open Source: The benchmark and dataset are publicly released for community evaluation and further research

Industry Insight

  • Benchmark designers and model evaluators should incorporate diagrammatic reasoning assessments alongside traditional answer-based metrics to obtain a more complete picture of model capabilities in spatial-mathematical tasks
  • Teams developing AI systems for education, CAD, or technical illustration should treat diagram construction as a separate capability requiring dedicated training and evaluation, rather than assuming it follows from reasoning proficiency
  • The 36.14% compile success rate suggests that current foundation models lack robust internal geometric simulation, pointing to opportunities for improvement through hybrid architectures combining symbolic reasoning with explicit spatial representation modules

TL;DR

  • 提出首个专门评估"图解推理"(diagrammatic reasoning)能力的奥林匹克几何基准测试,填补现有基准仅测量答案正确率的空白
  • 数据集包含954个自包含奥林匹克几何问题(其中297个难题),每个问题配有解决方案和人工编写的高保真Asymptote代码图
  • 当前基础模型在解题与画图之间存在显著能力鸿沟,平均编译成功率仅36.14%
  • 研究发现强数学推理能力并不等同于准确构建几何图形的能力

为什么值得看

该研究揭示了当前基础模型在几何推理中的关键盲区——能够解题不代表能画图,为评估AI的几何理解能力提供了全新维度。对AI从业者而言,这为构建更可靠的数学推理系统指明了需要突破的技术瓶颈。

技术解析

  • 数据集规模与结构:954个自包含奥林匹克几何问题,含297个难题子集,每个问题配有解决方案和人工编写的高保真Asymptote代码图
  • 评估指标体系:提出多维度评估框架,包括文本、代码、图像、VLM和约束条件等多种类型的度量指标
  • 核心发现:当前基础模型的平均编译成功率仅36.14%,表明模型生成的几何图形保真度显著低于预期
  • 技术定位:Asymptote是一种可渲染的矢量图形描述语言,用于精确表达几何构造和辅助线

行业启示

  • 数学推理能力的评估需要从"答案正确性"扩展到"过程可解释性",图解能力是验证模型真实理解几何关系的重要指标
  • 当前基础模型在几何构造方面存在系统性缺陷,未来研究应关注推理过程与可视化能力的协同提升
  • 该基准为几何AI应用(如教育、CAD辅助)提供了更严格的评估标准,推动模型从"解题机器"向"几何理解者"演进

Disclaimer: The above content is generated by AI and is for reference only. 免责声明:以上内容由 AI 生成,仅供参考。

Benchmark 基准测试 Evaluation 评测 Research 科学研究 LLM 大模型