中介思维模式：用于设计脚本编写的 LLM
Mediating Modes of Thought: LLM's for design scripting
AI总结：
本文提出多层 LLM 智能体系统，将自然语言设计意图转化为几何逻辑与软件命令并生成可视化脚本，验证其在有限复杂度内可降低设计脚本门槛。
摘要：
建筑师采用可视化脚本和参数化设计工具来探索更广阔的设计空间（Coates，2010），完善其对设计几何逻辑的思考（Woodbury，2010），并克服传统软件的限制（Burry，2011）。尽管二十年来人们一直努力让设计脚本编写更易使用，但设计师自由的思维方式与算法的刚性之间仍然存在脱节（Burry，2011）。大型语言模型（LLM）的最新进展表明，这种情况可能很快改变，因为 LLM 编码了对人类语境的普遍理解，并展现出生成几何逻辑的能力。本项目推测，如果 LLM 能够有效中介用户意图与算法之间的关系，它们将成为一种强大工具，使设计中的脚本编写更加普及且有趣。我们探索此类系统是否能够解释自然语言提示，以组合与计算设计脚本相关的几何操作。在该系统中，多层 LLM 智能体被配置了特定上下文，用于推断用户意图并构建顺序逻辑。给定用户的高层文本提示后，系统会创建几何描述，将其提炼为一系列逻辑操作，并映射到特定软件的命令。完成的脚本会在用户的可视化编程界面中构建出来。该系统能够成功生成不超过一定复杂度的完整可视化脚本，但超过这一复杂度阈值后则会失败。它展示了 LLM 如何使设计脚本编写与人类创造力和思维更加一致。未来研究应探索对话式交互，扩展至多模态输入和输出，并评估这些工具的性能。
英文摘要：
Architects adopt visual scripting and parametric design tools to explore more expansive design spaces (Coates, 2010), refine their thinking about the geometric logic of their design (Woodbury, 2010), and overcome conventional software limitations (Burry, 2011). Despite two decades of effort to make design scripting more accessible, a disconnect between a designer's free ways of thinking and the rigidity of algorithms remains (Burry, 2011). Recent developments in Large Language Models (LLMs) suggest this might soon change, as LLMs encode a general understanding of human context and exhibit the capacity to produce geometric logic. This project speculates that if LLMs can effectively mediate between user intent and algorithms, they become a powerful tool to make scripting in design more widespread and fun. We explore if such systems can interpret natural language prompts to assemble geometric operations relevant to computational design scripting. In the system, multiple layers of LLM agents are configured with specific context to infer the user intent and construct a sequential logic. Given a user's high-level text prompt, a geometric description is created, distilled into a sequence of logic operations, and mapped to software-specific commands. The completed script is constructed in the user's visual programming interface. The system succeeds in generating complete visual scripts up to a certain complexity but fails beyond this complexity threshold. It shows how LLMs can make design scripting much more aligned with human creativity and thought. Future research should explore conversational interactions, expand to multimodal inputs and outputs, and assess the performance of these tools.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
