Optimization Problem Solving Can Transition to Evolutionary Agentic Workflows
This addresses bottlenecks in industrial adoption of optimization methods by proposing a scalable, adaptive alternative to human-centric workflows.
The paper argues that optimization problem solving can shift from human-dependent to evolutionary agentic workflows, using foundation models and evolutionary search to autonomously handle problem formulation and algorithm selection, as demonstrated in case studies like cloud resource scheduling and ADMM parameter adaptation.
This position paper argues that optimization problem solving can transition from expert-dependent to evolutionary agentic workflows. Traditional optimization practices rely on human specialists for problem formulation, algorithm selection, and hyperparameter tuning, creating bottlenecks that impede industrial adoption of cutting-edge methods. We contend that an evolutionary agentic workflow, powered by foundation models and evolutionary search, can autonomously navigate the optimization space, comprising problem, formulation, algorithm, and hyperparameter spaces. Through case studies in cloud resource scheduling and ADMM parameter adaptation, we demonstrate how this approach can bridge the gap between academic innovation and industrial implementation. Our position challenges the status quo of human-centric optimization workflows and advocates for a more scalable, adaptive approach to solving real-world optimization problems.