Open Access

ARTICLE

STALAgent: A Multi-Agent System Based on Large Language Model (LLM) for Steel and Alloy Design

Jiayi Qiu¹, Youle Wang^1,*, Lei Zhang^1,2,*

1 Department of Internet Engineering, School of Software, Nanjing University of Information Science & Technology, Nanjing, China
2 Key Laboratory of Spectral Imaging Technology, Xi’an Institute of Optics and Precision Mechanics of the Chinese Academy of Sciences (CAS), Xi’an, China

* Corresponding Authors: Youle Wang. Email: ; Lei Zhang. Email:

Computers, Materials & Continua 2026, 89(1), 12 https://doi.org/10.32604/cmc.2026.084061

Received 15 April 2026; Accepted 16 July 2026; Issue published 13 August 2026

Abstract

The design of steel and alloy materials is of critical importance across a wide range of industrial applications; however, effective intelligent agent-based assistants for this domain remain limited. To address this gap, we introduce STALAgent, a large language model (LLM)-based multi-agent system specifically tailored for intelligent and automated design of steel and alloy materials. STALAgent is centered on an LLM brain with several key agents (e.g., task assignment, semantic search, inverse design, and heat treatment simulation) that collectively form a closed-loop workflow from user query to material recommendation. This system leverages a CrewAI-based orchestrator to assign tasks and coordinate a suite of specialized agents, including tools for knowledge retrieval using a retrieval augmented generation (RAG), inverse materials design using variational encoder (VAE), and thermodynamic calculations using Pycalphad. Through case studies involving inverse alloy design tasks and knowledge-based steel design queries, we showcase the capacity of the LLM agent to offer effective and dependable guidance for steel and alloy material design. STALAgent is practical and scalable, serving as a supplementary tool for materials researchers and holding promise for extension to other materials science domains requiring scientific discovery and domain knowledge-intensive tasks.

---

Keywords

---

Supplementary Material

Supplementary Material File

---