# Learning Virtual Machine Scheduling in Cloud Computing through Language Agents

arXiv: https://arxiv.org/abs/2505.10117 · HTML: https://mlsanity.com/paper/2505.10117/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 14 of its 59 references that are in the map.
- First posted on arXiv 15 May 2025.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 14 of 14)

- [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023)
- [ReEvo: Large Language Models as Hyper-Heuristics with Reflective Evolution](https://mlsanity.com/paper/2402.01145/) (2024)
- [NL4Opt Competition: Formulating Optimization Problems Based on Their Natural Language Descriptions](https://mlsanity.com/paper/2303.08233/) (2023)
- [ORLM: A Customizable Framework in Training Large Models for Automated Optimization Modeling](https://mlsanity.com/paper/2405.17743/) (2024)
- [Survey on Large Language Model-Enhanced Reinforcement Learning: Concept, Taxonomy, and Methods](https://mlsanity.com/paper/2404.00282/) (2024)
- [OptiMUS: Scalable Optimization Modeling with (MI)LP Solvers and Large Language Models](https://mlsanity.com/paper/2402.10172/) (2024)
- [LLMs Still Can't Plan; Can LRMs? A Preliminary Evaluation of OpenAI's o1 on PlanBench](https://mlsanity.com/paper/2409.13373/) (2024)
- [Contrastive Chain-of-Thought Prompting](https://mlsanity.com/paper/2311.09277/) (2023)
- [Online 3D Bin Packing with Constrained Deep Reinforcement Learning](https://mlsanity.com/paper/2006.14978/) (2020)
- [Hindsight Learning for MDPs with Exogenous Inputs](https://mlsanity.com/paper/2207.06272/) (2022)
- [Reinforcement Learning Driven Heuristic Optimization](https://mlsanity.com/paper/1906.06639/) (2019)
- [Robust and Adaptive Optimization under a Large Language Model Lens](https://mlsanity.com/paper/2501.00568/) (2024)
- [Learning from Contrastive Prompts: Automated Optimization and Adaptation](https://mlsanity.com/paper/2409.15199/) (2024)
- [VMAgent: Scheduling Simulator for Reinforcement Learning](https://mlsanity.com/paper/2112.04785/) (2021)

## Built on by (most cited first, 1 of 1)

- [InvEvolve: Evolving White-Box Inventory Policies via Large Language Models with Performance Guarantees](https://mlsanity.com/paper/2605.00369/) (2026)

## Abstract (arXiv)

In cloud services, virtual machine (VM) scheduling is a typical Online Dynamic Multidimensional Bin Packing (ODMBP) problem, characterized by large-scale complexity and fluctuating demands. Traditional optimization methods struggle to adapt to real-time changes, domain-expert-designed heuristic approaches suffer from rigid strategies, and existing learning-based methods often lack generalizability and interpretability. To address these limitations, this paper proposes a hierarchical language agent framework named MiCo, which provides a large language model (LLM)-driven heuristic design paradigm for solving ODMBP. Specifically, ODMBP is formulated as a Semi-Markov Decision Process with Options (SMDP-Option), enabling dynamic scheduling through a two-stage architecture, i.e., Option Miner and Option Composer. Option Miner utilizes LLMs to discover diverse and useful non-context-aware strategies by interacting with constructed environments. Option Composer employs LLMs to discover a composing strategy that integrates the non-context-aware strategies with the contextual ones. Extensive experiments on real-world enterprise datasets demonstrate that MiCo achieves a 96.9% competitive ratio in large-scale scenarios involving more than 10,000 virtual machines. It maintains high performance even under nonstationary request flows and diverse configurations, thus validating its effectiveness in complex and large-scale cloud environments.