SteelAgent: LLM-Orchestrated, Physics-Informed Steel Property Prediction with Audited Generalization and Calibrated Uncertainty

SteelAgent couples metallurgical descriptors and machine-learning models with a language-model interface for property prediction. For gradient boosting, pooled out-of-fold $R^2$ fell from 0.859 on a random split to 0.113 when steel families were held out. Empirical coverage of nominal 90% prediction intervals ranged from 91.0% under random splitting to 37.6% on held-out sources.