Adding New Capability in Existing Scientific Application with LLM Assistance

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Dubey, Anshu, Dhruv, Akash
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911247331491840
author Dubey, Anshu
Dhruv, Akash
author_facet Dubey, Anshu
Dhruv, Akash
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_00087
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Adding New Capability in Existing Scientific Application with LLM Assistance
Dubey, Anshu
Dhruv, Akash
Software Engineering
Artificial Intelligence
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.
title Adding New Capability in Existing Scientific Application with LLM Assistance
topic Software Engineering
Artificial Intelligence
url https://arxiv.org/abs/2511.00087