Cover
Volume 6, Issue 2 (2026) – 18 articles
Cover Picture: This cover illustrates the progressive evolution of materials science and engineering toward increasingly autonomous, agent-driven research. At the center, an AI agent ascends a luminous staircase representing the six autonomy levels, from Level 0 human-only workflows to the Level 5 vision of a fully autonomous AI materials scientist. The scenes at the two ends of the staircase further emphasize this transition, contrasting conventional human-led scientific work with a future autonomous AI scientist capable of independently driving the research cycle. The surrounding interconnected panels represent major materials research tasks, including knowledge extraction and hypothesis generation, materials design and property prediction, multiscale simulation, automated synthesis, and characterization and data analysis. These stages are linked through a network of information, computational tools, material structures, and experimental systems, reflecting the agent’s ability to coordinate heterogeneous resources rather than operate as an isolated predictive model. The radiant path at the top of the staircase points toward the still-emerging frontier of higher autonomy. Together, these elements visualize the roadmap of agentic materials science and engineering, in which increasing capabilities in planning, tool use, memory, self-reflection, and physical experimentation progressively connect knowledge, computation, and experiments toward autonomous materials discovery.
Back Cover
Volume 6, Issue 2 (2026) – 18 articles
Back Cover Picture: This cover presents a knowledge-enabled, data-driven framework for the intelligent design of ultra-strong and ductile near-α titanium alloys under extreme loading conditions. The central warhead and impact scene depict the intended application of near-α titanium alloys under high-speed impact and high-strain-rate loading. Under these conditions, adiabatic shear banding critically limits material performance, making the simultaneous improvement of dynamic strength and ductility a central challenge.
The blue stream on the left represents physics-informed metallurgical knowledge. It incorporates key performance parameters associated with electronic structure, phase stability, and mechanical response, including strain rate, Fermi energy, phase-formation parameters, the B/G ratio, and mixing enthalpy. The green stream on the right represents the data-driven pathway, consisting of alloy compositions and high-strain-rate experimental measurements reported in the literature. Integrating these complementary sources enables machine-learning models to establish interpretable relationships among alloy composition, physical descriptors, and mechanical properties, while efficiently exploring a complex multicomponent design space. The Pareto landscape illustrates the multi-objective optimization of strength, ductility, and metallurgical constraints, identifying candidate alloys that achieve improved strength-ductility synergy.
The Wisdom-Knowledge-Model-Data pathway symbolizes the connection between human intelligence and artificial intelligence, forming an integrated design paradigm for accelerating the development of advanced near-α titanium alloys for extreme service environments.
The blue stream on the left represents physics-informed metallurgical knowledge. It incorporates key performance parameters associated with electronic structure, phase stability, and mechanical response, including strain rate, Fermi energy, phase-formation parameters, the B/G ratio, and mixing enthalpy. The green stream on the right represents the data-driven pathway, consisting of alloy compositions and high-strain-rate experimental measurements reported in the literature. Integrating these complementary sources enables machine-learning models to establish interpretable relationships among alloy composition, physical descriptors, and mechanical properties, while efficiently exploring a complex multicomponent design space. The Pareto landscape illustrates the multi-objective optimization of strength, ductility, and metallurgical constraints, identifying candidate alloys that achieve improved strength-ductility synergy.
The Wisdom-Knowledge-Model-Data pathway symbolizes the connection between human intelligence and artificial intelligence, forming an integrated design paradigm for accelerating the development of advanced near-α titanium alloys for extreme service environments.
