Learning Virtual Machine Scheduling in Cloud Computing Through Language Agents

References

• Azar Y, Vainstein D (2019) Tight bounds for clairvoyant dynamic bin packing. ACM Trans. Parallel Comput. 6(3):1–21.Crossref, Google Scholar
• Azar Y, Cohen IR, Kamara S, Shepherd B (2013) Tight bounds for online vector bin packing. Boneh D, Roughgarden T, Feigenbaum J, eds. Proc. 45th Annual ACM Sympos. Theory Comput. (Association for Computing Machinery, New York), 961–970.Google Scholar
• Baykal-Gürsoy M, Gürsoy K (2010) Semi-Markov decision processes. Wiley Encyclopedia of Operations Research and Management Science, vol. 10. (John Wiley & Sons, Hoboken, NJ).Google Scholar
• Berg BP, Denton BT (2017) Fast approximation methods for online scheduling of outpatient procedure centers. INFORMS J. Comput. 29(4):631–644.Link, Google Scholar
• Bertsimas D, Margaritis G (2024) Robust and adaptive optimization under a large language model lens. Preprint, submitted December 31, https://arxiv.org/abs/2501.00568.Google Scholar
• Cao Y, Zhao H, Cheng Y, Shu T, Chen Y, Liu G, Liang G, Zhao J, Yan J, Li Y (2024) Survey on large language model-enhanced reinforcement learning: Concept, taxonomy, and methods. IEEE Trans. Neural Networks Learn. Systems 36(6):9737–9757.Crossref, Google Scholar
• Chen S, Moinzadeh K, Song JS, Zhong Y (2023) Cloud computing value chains: Research from the operations management perspective. Manufacturing Service Oper. Management 25(4):1338–1356.Link, Google Scholar
• Cheng Y, Zhao H, Zhou X, Zhao J, Cao Y, Yang C, Cai X (2025) A large language model for advanced power dispatch. Sci. Rep. 15(1):8925.Crossref, Google Scholar
• Chia YK, Chen G, Tuan LA, Poria S, Bing L (2023) Contrastive chain-of-thought prompting. Preprint, submitted November 15, https://arxiv.org/abs/2311.09277.Google Scholar
• Christensen HI, Khan A, Pokutta S, Tetali P (2017) Approximation and online algorithms for multidimensional bin packing: A survey. Comput. Sci. Rev. 24:63–79.Crossref, Google Scholar
• Coffman EG, Garey MR, Johnson DS (1983) Dynamic bin packing. SIAM J. Comput. 12(2):227–258.Crossref, Google Scholar
• Côté JF, Haouari M, Iori M (2021) Combinatorial benders decomposition for the two-dimensional bin packing problem. INFORMS J. Comput. 33(3):963–978.Link, Google Scholar
• Gartner (2024) Gartner forecasts worldwide public cloud end-user spending to total $723 billion in 2025. https://www.gartner.com/en/newsroom/press-releases/2024-11-19-gartner-forecasts-worldwide-public-cloud-end-user-spending-to-total-723-billion-dollars-in-2025.Google Scholar
• Gurobi Optimization, LLC (2024) Gurobi Optimizer reference manual. Accessed April 2024, https://www.gurobi.com.Google Scholar
• Hadary O, Marshall L, Menache I, Pan A, Greeff EE, Dion D, Dorminey S, et al. (2020) Protean:VM allocation service at scale. 14th USENIX Sympos. Operating Systems Design Implementation (USENIX Association, Berkeley, CA), 845–861.Google Scholar
• Huang C, Tang Z, Hu S, Jiang R, Zheng X, Ge D, Wang B, Wang Z (2025) ORLM: A customizable framework in training large models for automated optimization modeling. Oper. Res. 73(6):2986–3009.Link, Google Scholar
• Jiang Y, Cao Z, Zhang J (2021) Learning to solve 3D bin packing problem via deep reinforcement learning and constraint programming. IEEE Trans. Cybernetics 53(5):2864–2875.Crossref, Google Scholar
• Johnson DS (1973) Near-optimal bin packing algorithms. Unpublished PhD thesis, Massachusetts Institute of Technology, Cambridge.Google Scholar
• Kambhampati S, Valmeekam K, Guan L, Verma M, Stechly K, Bhambri S, Saldyt L, Murthy A (2024) Position: LLMs can’t plan, but can help planning in LLM-modulo frameworks. Salakhutdinov R, Kolter Z, Heller K, Weller A, Oliver N, Scarlett J, Berkenkamp F, eds. Proc. 41st Internat. Conf. Machine Learn., Proceedings of Machine Learning Research, vol. 235 (PMLR, New York), 22895–22907.Google Scholar
• Li C, Song D, Tao D (2023) Hit-MDP: Learning the SMDP option framework on MDPs with hidden temporal embeddings. Internat. Conf. Learn. Representations.Google Scholar
• Li M, Aggarwal K, Xie Y, Ahmad A, Lau S (2024) Learning from contrastive prompts: Automated optimization and adaptation. Preprint, submitted September 23, https://arxiv.org/abs/2409.15199.Google Scholar
• Li J, Gao Y, Yang Y, Bai Y, Zhou X, Li Y, Sun H, et al. (2025) Fundamental capabilities and applications of large language models: A survey. ACM Comput. Surveys 58(2):1–42.Google Scholar
• Lodi A (1999) Algorithms for two-dimensional bin packing and assignment problems. Unpublished PhD thesis, University of Bologna, Italy.Google Scholar
• Lodi A, Martello S, Vigo D (2009) Heuristic placement routines for two-dimensional bin packing. J. Math. Statist. 5(4):334–341.Crossref, Google Scholar
• Marler RT, Arora JS (2010) The weighted sum method for multi-objective optimization: New insights. Structural Multidisciplinary Optim. 41:853–862.Crossref, Google Scholar
• Martello S, Pisinger D, Vigo D (2000) The three-dimensional bin packing problem. Oper. Res. 48(2):256–267.Link, Google Scholar
• Nehra P, Kesswani N (2023) Efficient resource allocation and management by using load balanced multi-dimensional bin packing heuristic in cloud data centers. J. Supercomputing 79(2):1398–1425.Crossref, Google Scholar
• Romera-Paredes B, Barekatain M, Novikov A, Balog M, Kumar MP, Dupont E, Ruiz FJ, et al. (2024) Mathematical discoveries from program search with large language models. Nature 625(7995):468–475.Crossref, Google Scholar
• Sheng J, Hu Y, Zhou W, Zhu L, Jin B, Wang J, Wang X (2022) Learning to schedule multi-NUMA virtual machines via reinforcement learning. Pattern Recognition 121:108254.Crossref, Google Scholar
• Sinclair SR, Frujeri FV, Cheng CA, Marshall L, Barbalho HDO, Li J, Neville J, Menache I, Swaminathan A (2023) Hindsight learning for MDPs with exogenous inputs. Krause A, Brunskill E, Cho K, Engelhardt B, Sabato S, Scarlett J, eds. Proc. 40th Internat. Conf. Machine Learn., Proceedings of Machine Learning Research, vol. 202 (PMLR, New York), 31877–31914.Google Scholar
• Stolyar AL (2013) An infinite server system with general packing constraints. Oper. Res. 61(5):1200–1217.Link, Google Scholar
• Sutton RS, Precup D, Singh S (1999) Between MDPs and semi-MDPs: A framework for temporal abstraction in reinforcement learning. Artificial Intelligence 112(1–2):181–211.Crossref, Google Scholar
• Tang X, Liu F, Wang B, Xu D, Jiang J, Wu Q, Chen CP (2024) Workflow scheduling based on asynchronous advantage actor–critic algorithm in multi-cloud environment. Expert Systems Appl. 258:125245.Crossref, Google Scholar
• Tang X, Liu F, Xu D, Jiang J, Tang Q, Wang B, Wu Q, Chen CP (2025) LLM-assisted reinforcement learning: Leveraging lightweight large language model capabilities for efficient task scheduling in multi-cloud environment. IEEE Trans. Consumer Electronics 71(2):5631–5644.Crossref, Google Scholar
• Wang L, Ma C, Feng X, Zhang Z, Yang H, Zhang J, Chen Z, et al. (2024) A survey on large language model based autonomous agents. Frontiers Comput. Sci. 18(6):186345.Crossref, Google Scholar
• Wu J, Wang Z, Sheng J, Li W, Wang X, Luo J (2026) Learning virtual machine scheduling in cloud computing through language agents. https://doi.org/10.1287/ijoc.2025.1368.cd, https://github.com/INFORMSJoC/2025.1368.Google Scholar
• Yang Y, Sun H, Li J, Liu R, Li Y, Liu Y, Gao Y, Huang H (2024) MindLLM: Lightweight large language model pre-training, evaluation and domain application. AI Open 5:155–180.Crossref, Google Scholar
• Zhang Z, Denton BT, Xie X (2020) Branch and price for chance-constrained bin packing. INFORMS J. Comput. 32(3):547–564.Link, Google Scholar