English

Adding New Capability in Existing Scientific Application with LLM Assistance

Software Engineering 2025-11-04 v1 Artificial Intelligence

Abstract

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.

Keywords

Cite

@article{arxiv.2511.00087,
  title  = {Adding New Capability in Existing Scientific Application with LLM Assistance},
  author = {Anshu Dubey and Akash Dhruv},
  journal= {arXiv preprint arXiv:2511.00087},
  year   = {2025}
}

Comments

8 pages, 4 figures, submitted to The 1st International Workshop on Foundational large Language Models Advances for HPC in Asia

R2 v1 2026-07-01T07:16:11.915Z