2 papers
cond-mat.mtrl-sci2026
Agentic Design of Compositional Descriptors via Autoresearch for Materials Science Applications
Matteo Cobelli, Stefano Sanvito
Autoresearch offers a flexible paradigm for automating scientific tasks, in which an AI agent proposes, implements, evaluates, and refines candidate solutions against a quantitativ…
cs.CL2024
Sampling Latent Material-Property Information From LLM-Derived Embedding Representations
Luke P. J. Gilligan, Matteo Cobelli, Hasan M. Sayeed +2
Vector embeddings derived from large language models (LLMs) show promise in capturing latent information from the literature. Interestingly, these can be integrated into material e…