Self-Refining Topology Optimization via an LLM-Based Multi-Agent Framework

2026-05-22

AI Summary

This work addresses the reliance on expert knowledge in multi-stage decision-making within topology optimization, which hinders full automation. To overcome this limitation, the authors propose TopOptAgents—a six-agent system powered by large language models (LLMs)—that introduces, for the first time in this domain, a multi-agent collaborative framework integrated with an iterative self-refinement mechanism. Through closed-loop iterations encompassing problem modeling, validation, code generation and execution, and solution quality assessment, the system enables end-to-end automated decision-making. The approach substantially enhances the reliability and generalization capability of LLMs in low-prior-knowledge scenarios, successfully generating convergent design solutions for complex problems where literature and open-source resources are scarce, and significantly outperforming single-LLM baselines.

Abstract

Topology optimization is a widely used design method that produces optimized material distributions for prescribed objectives and constraints through well-established numerical algorithms. Throughout the workflow, engineers make a series of decisions ranging from setting and adjusting numerical parameters to assessing whether the converged design meets considerations beyond those explicitly included in the optimization problem, such as physical feasibility. These decisions, which draw on domain expertise, interfere with the autonomous design process. To address this difficulty, this study presents TopOptAgents, a multi-agent system for automating not only the design process but also decision-making during the key stages of the topology optimization process. TopOptAgents consists of six LLM-based agents collaborating through iterative self-refinement cycles spanning problem formulation, validation, code generation and execution, and quality assessment of the optimized structure. This process enables error correction and progressive improvement of both the optimization setup and resulting design. The framework is demonstrated on optimization problems selected to cover a range of settings that differ in their literature coverage and numerical characteristics The benefits of iterative self-refinement are found to be particularly pronounced for problem classes where the pretrained language model has limited prior exposure, such as formulations whose literature and open-source implementations are comparatively sparse. In such cases, the proposed framework reliably produces converged designs where a single state-of-the-art LLM struggles, suggesting that self-refinement broadens the range of topology optimization problems that LLM-based automation can reliably address.

Problem

• topology optimization
• autonomous design
• decision-making
• engineering expertise
• design automation

Innovation

• topology optimization
• large language model (LLM)
• multi-agent system
• self-refinement
• automated design