TBU Publications
Repository of TBU Publications

LLM-based optimization framework: An architectural overview

DSpace Repository

Show simple item record


dc.title LLM-based optimization framework: An architectural overview en
dc.contributor.author Kováč, Jozef
dc.contributor.author Kadavý, Tomáš
dc.contributor.author Viktorin, Adam
dc.contributor.author Šenkeřík, Roman
dc.relation.ispartof Array
dc.identifier.issn 2590-0056 Scopus Sources, Sherpa/RoMEO, JCR
dc.date.issued 2026
utb.relation.volume 31
dc.type article
dc.language.iso en
dc.publisher Elsevier B.V.
dc.identifier.doi 10.1016/j.array.2026.101056
dc.relation.uri https://www.sciencedirect.com/science/article/pii/S2590005626003796
dc.relation.uri https://www.sciencedirect.com/science/article/pii/S2590005626003796/pdfft?md5=fff1a95e5758e34c9b4b5622d02146cd&pid=1-s2.0-S2590005626003796-main.pdf
dc.subject Algorithmic solution evolution en
dc.subject Software architecture en
dc.subject Optimization en
dc.subject Iterative improvement en
dc.subject Large language models en
dc.description.abstract This paper provides a detailed analysis of the potential technical and architectural challenges associated with building the FrontEASE software. FrontEASE serves as the web wrapper, utility extension, and user interaction layer for the modular LLM-based optimization framework, EASE (Effortless Algorithmic Solution Evolution). The focus is on the architectural choices made and how this unconventional solution, designed to streamline the use of LLM-based optimization workflows for scientific applications, aligns with best practices in standard software engineering. The primary goal of this paper is to promote and facilitate further experimentation with enterprise-grade architectures for LLM-driven applications. Ultimately, this work aims to guide the development of these products into reliable and maintainable software solutions over the long term. en
utb.faculty Faculty of Applied Informatics
dc.identifier.uri http://hdl.handle.net/10563/1012898
utb.identifier.scopus 2-s2.0-105044422224
utb.identifier.wok 001822035700001
utb.source j-scopus
dc.date.accessioned 2026-11-20T08:16:40Z
dc.date.available 2026-11-20T08:16:40Z
dc.description.sponsorship The research presented in this paper was supported by the Internal Grant Agency of Tomas Bata University in Zlin [114] , under project number IGA/CebiaTech/2026/004 , and by the resources of the A.I. Lab [110] at the Faculty of Applied Informatics, Tomas Bata University in Zlin ( ailab.fai.utb.cz ).
dc.description.sponsorship Internal Grant Agency of Tomas Bata University in Zlin [IGA/CebiaTech/2026/004]; Faculty of Applied Informatics, Tomas Bata University in Zlin
dc.rights Attribution 4.0 International
dc.rights.uri http://creativecommons.org/licenses/by/4.0/
dc.rights.access openAccess
utb.ou Department of Informatics and Artificial Intelligence
utb.contributor.internalauthor Kováč, Jozef
utb.contributor.internalauthor Kadavý, Tomáš
utb.contributor.internalauthor Viktorin, Adam
utb.contributor.internalauthor Šenkeřík, Roman
utb.fulltext.sponsorship The research presented in this paper was supported by the Internal Grant Agency of Tomas Bata University in Zlin [114], under project number IGA/CebiaTech/2026/004, and by the resources of the A.I. Lab [110] at the Faculty of Applied Informatics, Tomas Bata University in Zlin ( ailab.fai.utb.cz).
utb.fulltext.projects IGA/CebiaTech/2026/004

Files in this item

Files Size Format View

There are no files associated with this item.

Show simple item record

Attribution 4.0 International Except where otherwise noted, this item's license is described as Attribution 4.0 International