Regarding context size in LLM-based metaheuristic design
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F70883521%3A28140%2F25%3A63599958" target="_blank" >RIV/70883521:28140/25:63599958 - isvavai.cz</a>
Result on the web
<a href="http://dx.doi.org/10.1145/3712255.3734351" target="_blank" >http://dx.doi.org/10.1145/3712255.3734351</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1145/3712255.3734351" target="_blank" >10.1145/3712255.3734351</a>
Alternative languages
Result language
angličtina
Original language name
Regarding context size in LLM-based metaheuristic design
Original language description
The recent and rapid progress in large language models (LLMs) has markedly influenced research efforts in the automated design and configuration of metaheuristic algorithms. A common limitation of contemporary LLMs is their finite context window, which constrains the amount of information they can effectively utilize during generation. In this study, we investigate the role of conversational context in the metaheuristic design process. This study explores two distinct aspects of LLM-based metaheuristic design: (1) the effect of conversational context on the performance of generated optimizers, and (2) its influence on the validity of generated code. Both are investigated using the EASE framework. The findings yield several unexpected insights, which are discussed in detail in the paper, offering a deeper understanding of how context affects the reliability and effectiveness of LLM-assisted algorithm generation.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
—
Continuities
S - Specificky vyzkum na vysokych skolach
Others
Publication year
2025
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
PROCEEDINGS OF THE 2025 GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE COMPANION, GECCO 2025 COMPANION
ISBN
979-8-4007-1464-1
ISSN
—
e-ISSN
—
Number of pages
9
Pages from-to
2345-2353
Publisher name
Association for Computing Machinery, Inc
Place of publication
New York
Event location
Malaga
Event date
Jul 14, 2025
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
001564494900376