让文字生成的物理图严格遵守物理定律，避免错误的力矢量和几何错乱。
PhyDrawGen: Physically Grounded Diagram Generation from Natural Language
- 用大模型提取场景图，再由确定性求解器转为精确几何结构。
- 在1449个物理问题上，准确率显著优于GPT-5、Gemini等主流模型。
- 适合需要高物理正确性的教育、科研或工程可视化场景。
从自然语言生成物理图需要严格遵循物理定律。当前生成模型虽视觉逼真，却常出现力矢量幻觉、违背守恒律及几何约束。我们提出PhyDrawGen，一种神经符号流水线，将语义场景理解与物理约束满足分离。首先，大语言模型从问题文本中提取类型化场景图；接着，确定性求解器将其转换为平面直线图（PSLG），以精确几何原语编码力平衡、光路和场拓扑；最后，微调后的Qwen-VL模型执行视觉引导的提出-验证循环，迭代修正约束违反。在涵盖力学、光学和电磁学的1449个问题基准上评估，PhyDrawGen显著优于GPT-5-image、Gemini 2.5 Flash和Gemini 3 Pro，即使在罕见物体问题上也保持强物理准确性。
原文摘要 · Abstract (English)
Generating physics diagrams from text requires strict adherence to physical laws. While current generative models produce visually plausible outputs, they systematically hallucinate force vectors, ignore conservation laws, and violate geometric constraints. We present PhyDrawGen, a neuro-symbolic pipeline that decouples semantic scene understanding from physical constraint satisfaction. First, a large language model extracts a typed scene graph from the problem text. A deterministic solver then converts this graph into a Planar Straight-Line Graph (PSLG), encoding force balance, optical paths, and field topologies as exact geometric primitives. Finally, a fine-tuned Qwen-VL model implements a visually grounded propose-verify loop to iteratively correct any constraint violations. Evaluated on a benchmark of 1,449 problems spanning mechanics, optics, and electromagnetism, PhyDrawGen significantly outperforms GPT-5-image, Gemini 2.5 Flash, and Gemini 3 Pro, demonstrating robust physical accuracy even on unusual-object problems.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。