Could LLMs Predict Algorithm Performance in Automated Design of Metaheuristics?
Open Access
- 13 July 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 1416-1424
Abstract
No abstract availableFunding Information
- National Science Centre Poland (ARTIQ/0004/2021)
This publication has 8 references indexed in Scilit:
- Code Evolution Graphs: Understanding Large Language Model Driven Design of Algorithms2025
- On the Effectiveness of LLM-as-a-Judge for Code Generation and SummarizationIEEE Transactions on Software Engineering, 2025
- LLaMEA: A Large Language Model Evolutionary Algorithm for Automatically Generating MetaheuristicsIEEE Transactions on Evolutionary Computation, 2024
- Evaluating Source Code Quality with Large Language Models: a comparative study2024
- A Critical Examination of Large Language Model Capabilities in Iteratively Refining Differential Evolution Algorithm2024
- Hot or Cold? Adaptive Temperature Sampling for Code Generation with Large Language ModelsProceedings of the AAAI Conference on Artificial Intelligence, 2024
- Leveraging Large Language Models for the Generation of Novel Metaheuristic Optimization Algorithms2023
- A Complexity MeasureIEEE Transactions on Software Engineering, 1976