Presentation Information

[S3.15]Auditable LLM-Guided Compositional Design of Super MoSiBTiC Alloys

○Xinyu Yan1, Kyosuke Yoshimi1 (1. Tohoku Univ.)

Keywords:

Large language model,MoSiBTiC alloy,Ultra-high-temperature structural materials,Auditable alloy design

We develop an auditable LLM-driven multi-agent framework to design Super MoSiBTiC alloys for ultra-high-temperature applications. Literature-derived composition-property rules guide a ReAct agent to generate candidates, screened via CALPHAD phase stability, Pareto ranking, and Monte Carlo analysis.

Comment

To browse or post comments, you must log in.Log in