Graph-Based Task Allocation for Multi-Agent Fleet Management: A Genetic Algorithm Approach with LLM Integration
Applied Sciences · 15.04.2026 · 16 (8) · 3851
DOI: 10.3390/app16083851 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 15.04.2026. Verfasst von Beril Yalcinkaya und 3 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: European Union’s Horizon Europe Framework Programme, FCT—Fundação para a Ciência e a Tecnologia.
Abstract (Originalsprache)
Efficient task allocation and coordination are critical for heterogeneous multi-agent systems operating in dynamic field environments. This paper presents a closed-loop framework that integrates Large Language Models (LLMs) with graph-based optimisation to enable end-to-end task decomposition, allocation, and adaptive execution. High-level task scripts are initially parsed by an LLM into structured execution flows, which are transformed into Directed Acyclic Graphs (DAGs) capturing action-level dependencies. A Genetic Algorithm (GA) then optimises agent-to-task assignments by minimising makespan under capability and battery constraints. To ensure robustness, the framework incorporates an LLM-driven recovery module that enables localised replanning under execution failures without interrupting unaffected agents. System-level experiments in a high-fidelity agroforestry simulation demonstrate a 37% increase (p
Förderung
- European Union’s Horizon Europe Framework Programme
- FCT—Fundação para a Ciência e a Tecnologia
Zitieren
APA
Yalcinkaya, B., Couceiro, M. S., Soares, S., & Valente, A. (2026). Graph-Based Task Allocation for Multi-Agent Fleet Management: A Genetic Algorithm Approach with LLM Integration. Applied Sciences, 16(8), 3851. https://doi.org/10.3390/app16083851
Vancouver
Yalcinkaya B, Couceiro MS, Soares S, Valente A. Graph-Based Task Allocation for Multi-Agent Fleet Management: A Genetic Algorithm Approach with LLM Integration. Applied Sciences. 2026;16(8):3851. doi:10.3390/app16083851
BibTeX
@article{Yalcinkaya2026,
author = {Yalcinkaya, Beril and Couceiro, Micael S. and Soares, Salviano and Valente, António},
title = {Graph-Based Task Allocation for Multi-Agent Fleet Management: A Genetic Algorithm Approach with LLM Integration},
journal = {Applied Sciences},
year = {2026},
volume = {16},
number = {8},
pages = {3851},
doi = {10.3390/app16083851}
}
EUVIMED