用大模型辅助从零编写新算法代码，提升科研工具扩展能力
Adding New Capability in Existing Scientific Application with LLM Assistance
- 基于大模型生成全新算法代码，无需历史示例
- 改进代码翻译工具Code-Scribe，支持新代码生成
- 适合需要快速实现新算法的科研人员
随着大语言模型（LLM）的兴起与快速发展，自动化编程已成为重要研究方向。尽管已有大量工作探讨模型生成代码的能力与效果，但针对新算法的代码生成仍缺乏深入探索——训练数据中未包含相似代码示例。本文提出一种新方法，利用大模型辅助从零开始编写新算法代码，并对已有的代码翻译工具Code-Scribe进行改进，以支持新代码生成。该方法可有效拓展科研应用的代码能力，为算法快速实现提供支持。
原文摘要 · Abstract (English)
With the emergence and rapid evolution of large language models (LLM), automating coding tasks has become an important research topic. Many efforts are underway and literature abounds about the efficacy of models and their ability to generate code. A less explored aspect of code generation is for new algorithms, where the training dataset would not have included any previous example of similar code. In this paper we propose a new methodology for writing code from scratch for a new algorithm using LLM assistance, and describe enhancement of a previously developed code-translation tool, Code-Scribe, for new code generation.
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。