报告题目：Learning Virtual Machine Scheduling in Cloud Computing through Language Agents

报告摘要：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 micro-macro hierarchical architecture, i.e., Option Miner and Option Composer. Option Miner utilizes LLMs to discover different 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 a real-world enterprise dataset demonstrate that MiCo achieves a 96.9% performance ratio under large-scale and nonstationary scenarios. It maintains high performance even under nonstationary request flows and different configurations, thereby validating its effectiveness in complex and large-scale cloud environments.

报告人介绍 ：罗俊，上海交通大学安泰经济与管理学院教授，博士生导师，上海交通大学行业研究院副院长。主要研究方向包括随机仿真与大数据分析，服务运营管理，供应链物流管理，金融风险管理等。主持国家自然科学基金委重点项目，国家优秀青年科学基金项目等。在Operations Research，INFORMS Journal on Computing等国际期刊上发表论文30余篇。曾获得中国教育部第八届高等学校科学研究优秀成果奖(人文社会科学)二等奖，上海交通大学首届“教书育人奖”（三等奖）等荣誉奖励。目前担任Naval Research Logistics副编辑，《系统管理学报》编辑部主任，管理科学与工程学会和中国系统工程学会理事，中国运筹学会和中国“双法”研究会等多个二级分会副主任委员/副理事长/常务理事等。