Search

In the evolving landscape of computational and data-driven materials engineering, the integration of machine learning and high-throughput methodologies has accelerated discovery processes, yet it introduces a paradox where rapid optimization often bypasses deep scientific understanding. This manuscript presents a systems theory perspective on black-box optimization in autonomous materials engineering, emphasizing closed-loop labs where AI-driven decisions guide experimentation without explicit interpretability. Drawing from materials informatics and representation learning, we identify the discovery acceleration paradox: enhanced efficiency in inverse design and property prediction erodes traditional epistemic structures, leading to reliance on opaque models. We introduce the "Epistemic Opaque Discovery System" (EODS) framework, which conceptualizes materials discovery as a layered network of data infrastructures, model architectures, and feedback mechanisms. This framework highlights trade-offs between optimization speed and interpretability, incorporating uncertainty quantification to mitigate risks in autonomous systems. Implications extend to simulation-experiment coupling and multimodal datasets, suggesting pathways for balanced computational workflows that preserve scientific insight amid black-box dominance. By reframing discovery pipelines, EODS offers a theoretical lens for engineering resilient AI ecosystems in materials science, fostering sustainable innovation without sacrificing foundational knowledge.