The integration of Artificial Intelligence (AI) with fracture simulation is revolutionizing predictive modeling, enabling unprecedented accuracy and efficiency in computational mechanics. This mini-symposium focuses on advancing AI-driven methods for fracture simulation in engineering applications, addressing key challenges in crack propagation, material failure, and simulation optimization. We invite contributions on topics including but not limited to: • AI-enhanced fracture propagation models for accelerated and high-fidelity simulations in engineering systems. • Physics-informed neural networks/operators for predictive modeling of brittle and ductile fracture in structural components. • Deep learning for inverse problems in fracture mechanics and damage assessment of engineered materials. • Surrogate modeling with neural networks to enable real-time fracture analysis in industrial applications. • Uncertainty quantification in AI-augmented fracture prediction for reliable engineering solutions. The mini-symposium aims to enhance AI methodologies specifically for fracture simulation in engineering contexts, bridging the gap between fundamental research and industrial applications. Researchers from computational mechanics, materials science, and applied AI are encouraged to participate, sharing insights on next-generation simulation tools that combine physics-based modeling with data-driven approaches for engineering challenges.