Abstract
Body-centered cubic (bcc) alloys can achieve gigapascal-level yield strengths but typically are limited in tensile ductility (<20%), contrasting sharply with elemental metals (the largest elongation of ~50%). Multi-principal-element alloys offer vast compositional space to reach synergistic strength-ductility combinations. However, combinatorial trial-and-error exploration is prohibitively costly, while machine learning (ML) approaches are hindered by data scarcity. Here, we develop an ML-guided framework integrating active learning with physics-informed Bayesian optimization to rapidly converge on optimal compositions. The resulting Ti(36)V(14)Nb(22)Hf(22)Zr(1)Al(5) alloy achieves a yield strength of 953 MPa and a large tensile ductility of 42%. The high strength arises from the substantial lattice distortion, as well as the ~1-nm-sized local chemical fluctuations (LCFs) inherent to the highly concentrated bcc solid solution. The ubiquitous LCFs also substantially promote dislocation multiplication and strain hardening, enabling a large tensile ductility. Our approach demonstrates ML's efficacy in accelerating the finding of high-performance alloys.