Conference Logo ProgramMaster Logo
Conference Tools for 2026 TMS Annual Meeting & Exhibition
Login
Register as a New User
Help
Submit An Abstract
Propose A Symposium
Presenter/Author Tools
Organizer/Editor Tools

About this Abstract
Meeting 2026 TMS Annual Meeting & Exhibition
Symposium Artificial Intelligence Applications in Integrated Computational Materials Engineering (AI-ICME)
Presentation Title Using Agentic AI Programming Tools for ICME Code Development
Author(s) Theron M. Rodgers
On-Site Speaker (Planned) Theron M. Rodgers
Abstract Scope Agentic programming tools, such as Claude Code and Gemini CLI, are surging in popularity and giving rise to “vibe coding,” where a Large Language Model (LLM) generates computer code rather than being manually written by a developer. This programming methodology has great potential to accelerate software development; however, it also presents several pitfalls, including creating poorly understood code, misinterpreting user instructions, and rapidly inflating codebase size. This presentation will detail hands-on experience using agentic tools with the open-source SPPARKS mesoscale simulation code. It will discuss the strengths of this approach, along with the observed pitfalls. Additionally, it will detail the positive impacts that agentic programming can have on ICME workflows, including improved code documentation and refactoring, enhanced reusability of research codes, and streamlined data transfer and interfaces between computational tools.
Proceedings Inclusion? Planned:
Keywords Computational Materials Science & Engineering, Machine Learning, ICME

OTHER PAPERS PLANNED FOR THIS SYMPOSIUM

AI Augmented Molecular Dynamics Modeling of Novel Zeolite Nano Resins for Targeted Advanced Water Treatment
AI for Alloy Design in Extreme Environments
AlloyGPT 2.0: Develop A Self-Adaptive Multi-Agent Autonomous Framework for Additive Manufacturable Alloy Design
An Extensible, Data-Driven Platform for Automated Atomic Structure Analysis
Analyzing Microstructural Interactions in Materials Using Explainable Neural Networks
Artificial Intelligence for Additive Manufacturing
Automated Implementation of Axiomatic Design for Materials System Chart Using Large Language Models
Autonomous Fractography Analysis Framework Driven by Large Language Models
Blacksmithing AI: Using a Large Language Model to Predict Workpiece Shapes and Manufacturing Operations for Automated Manufacturing
Breaking Boundaries: Texture-Aware AI for Metallography
Data-Driven Design of Two-Phase Metallic Spinodoids for Thermomechanical Properties
Development of Machine Learning Interatomic Potentials for Ni-Al-Ti Systems to Study γ/γ' Phase Properties in Superalloys
From CALPHAD to AI: High-Throughput Pathways for Functionally Graded Alloy Design and Additive Manufacturing
Generative AI–Driven Process–Structure–Property Optimization for Materials Discovery
Graph Neural Network-Based Forecasting of Atomic Dynamics at Grain Boundaries
H-13: Establishing a Large Language Model-based Systematic Alloy Design Strategy for Advanced Titanium Alloys
H-14: Ionic Transport Properties and Phase Stability of Solid Electrolyte Material Li7La3Zr2O12: A Deep-Neural-Network Molecular Dynamics Investigation
H-15: Machine-Learned Force Field for the Energetic Molecular Crystal LLM-105
Harnessing AI for Prediction of Abnormal Grain Growth Using 3D Experimental Data
Integrating Microstructural, Diffraction, and Compositional Data for Predictive Materials Modeling
Large Language Model Agents for Atomistic Simulation Workflows
Leveraging Large Language Models for Inverse Design of Processing Parameters in Materials Engineering
Machine Learning-Augmented Finite Volume Modeling and Inverse Optimization of Velocity and Pressure Distribution of Bentonite Slurry in Slurry Shield Tunneling Applications
Machine Learning Prediction of Antioxidant Additive Performance from Atomistic Simulations
ML-Accelerated ICME Framework for Solid Phase Processing of Nuclear Cladding Materials
Physics-Constrained Neural Network for Increased Generalizability in Predicting Material Microstructure Evolution
Physics-Informed Neural–Cellular Framework for Predicting Grain Morphology and Microstructural Evolution in Metal Additive Manufacturing Simulation
Quantifying Relationship Between Creep and Microstructure of Metals Using Symbolic Regression
Reward Engineering in AI-Driven Materials Discovery and Design
Robust Physics-Informed Neural Networks for Modeling Oxide Film Growth in Corrosion Science
Toward an Interactive AI-Enabled Platform for Critical Materials Reduction: From Forecasting to Processing
Toward DFT-Accurate Modeling of HfNbTaTiZr High Entropy Alloy Using Moment Tensor Potential
Using Agentic AI Programming Tools for ICME Code Development
Questions about ProgramMaster? Contact programming@programmaster.org | TMS Privacy Policy | Accessibility Statement