AI RESEARCH
Agentic Design of Compositional Descriptors via Autoresearch for Materials Science Applications
arXiv CS.AI
•
ArXi:2605.14671v1 Announce Type: cross Autoresearch offers a flexible paradigm for automating scientific tasks, in which an AI agent proposes, implements, evaluates, and refines candidate solutions against a quantitative objective. Here, we use composition-based materials-property prediction to test whether such agents can perform a task beyond model selection and hyperparameter optimization: the design of input descriptors. We