Investigating the Use of Large Language Models for Task Scheduling

• Lívia Mayumi Kawasaki Alves UDESC
• Guilherme Piêgas Koslovski UDESC

DOI: https://doi.org/10.5753/eradrs.2025.6808

Abstract

Large Language Models (LLMs) have revolutionized the field of Natural Language Processing (NLP), and it is now possible to adapt these models to perform complex tasks across various domains. Specifically, the fine-tuning technique allows pre-trained models to enhance their knowledge for specific functions. This paper aims to propose an analysis of the use of fine-tuned LLMs to assist in scheduling communicative tasks, that is, the process of allocating system resources to various tasks, meeting specific objectives.

References

Abgaryan, H., Harutyunyan, A., and Cazenave, T. (2024). Llms can schedule. arXiv preprint [link].

Brucker, P. (2006). Scheduling Algorithms. Springer.

Feitelson, D. G. and Rudolph, L. (1998). Metrics and benchmarking for parallel job scheduling. In Feitelson, D. G. and Rudolph, L., editors, Job Scheduling Strategies for Parallel Processing, pages 1–24, Berlin, Heidelberg. Springer Berlin Heidelberg.

Parthasarathy, V. B., Zafar, A., Khan, A., and Shahid, A. (2024). The ultimate guide to fine-tuning llms from basics to breakthroughs: An exhaustive review of technologies, research, best practices, applied research challenges and opportunities.

Prince, S. J. (2023). Understanding Deep Learning. MIT Press.

Yenduri, G., Ramalingam, M., Selvi, G. C., Supriya, Y., Srivastava, G., Maddikunta, P. K. R., Raj, G. D., Jhaveri, R. H., Prabadevi, B., Wang, W., Vasilakos, A. V., and Gadekallu, T. R. (2024). GPT (generative pre-trained transformer)—a comprehensive review on enabling technologies, potential applications, emerging challenges, and future directions. IEEE Access, 12:54608–54649. DOI: 10.1109/ACCESS.2024.3385584