In materials science and engineering design, high-fidelity and high-efficiency numerical simulation has become a driving force for innovation and practical implementation. To address longstanding bottlenecks in the development of conventional material constitutive models—such as lengthy modeling cycles and difficulties in numerical implementation—this study proposes an intelligent modeling and code generation approach powered by large language models. A structured knowledge base integrating constitutive theory, numerical algorithms, and UMAT (User Material) interface specifications is constructed, and a retrieval-augmented generation strategy is employed to establish an end-to-end workflow spanning experimental data parsing, constitutive model formulation, and automatic UMAT subroutine generation. Experimental results show that the method achieves high accuracy for both a classical Johnson–Cook model and a physics-informed neural network (PINN) model, with key parameter identification errors below 5%. Moreover, the automatically generated UMAT subroutines yield finite element simulation results in Abaqus that are highly consistent with theoretical predictions (coefficient of determination R² > 0.98) while maintaining good numerical stability. This framework is currently focused on the automatic construction of rate-dependent elastoplastic material models, and its core method also provides a clear path for extending to other constitutive categories such as hyperelasticity and viscoelasticity. This work provides an effective technical route for the rapid development and reliable numerical implementation of material constitutive models, significantly advancing the intelligence level of computational mechanics research and improving engineering application efficiency.

This paper provides a comprehensive review of recent advances in multi-scale modeling for simulating dynamic damage and fracture in metallic materials, a critical area due to the widespread application of metals and their susceptibility to complex failure in engineering practice. The paper first outlines the mechanisms of damage evolution and crack propagation across different spatial and temporal scales. It then introduces commonly used simulation approaches spanning micro- to macro-scales for studying damage and fracture in metals, analyzing the evolution of mechanical properties from defect initiation to ultimate failure, and elucidating the underlying damage mechanisms at different scales. Finally, the review summarizes multi-scale coupling strategies and mechanisms, as well as the integration of machine learning (ML) into multi-scale frameworks. These advanced approaches are recognized as key tools for improving predictive accuracy and computational efficiency, facilitating the scalability of multi-scale damage modeling for metallic materials in large-scale engineering applications and digital twin platforms. This review aims to provide a theoretical foundation for future research toward more reliable, efficient, and predictive multi-scale modeling of metallic materials.