Breaking equiatomic constraints: knowledge-enhanced AI framework for function-oriented single-phase high-entropy alloy design

High-entropy alloys exhibit exceptional performance under extreme environments; however, conventional equiatomic or near-equiatomic design paradigms restrict exploration of single-phase solid-solution spaces, leaving many non-equiatomic compositions unexplored. Here, we propose a knowledge-enhanced AI framework integrating physics-guided machine learning with large language model (LLM) agents to explore compositions beyond equiatomic constraints. Machine learning models trained on physics-based descriptors achieve F1-scores of 0.96 and 0.94 for face-centered cubic (FCC) and body-centered cubic (BCC) phase prediction, respectively. Two substantially non-equiatomic alloys—Al 28 Cr 22 Fe 26 Ni 15 Mo 9 (BCC) and Co 23 Cr 15 Fe 25 Ni 31 Mo 6 (FCC)—experimentally confirm reliable phase prediction within the investigated compositional domain. LLM-guided reasoning on oxidation mechanisms further enables the design of Co 22 Cr 24 Fe 20 Ni 25 Mo 5 Mn 4 , which exhibits a steady-state oxidation rate constant of 1.41 × 10 −8 mg n cm −2 n h −1 (50–100 h, n = 45.35) at 900 °C, indicative of self-limiting oxidation kinetics. This superior performance is attributed to the formation of a stable Cr 2 O 3 /(Mn,Fe)Cr 2 O 4 bilayer oxide scale operating via a synergistic barrier–buffer protection mechanism. This study presents a data-efficient, AI-assisted methodology for intelligent HEA design in high-dimensional compositional spaces.