Agentic programs: an emerging form of scientific software in computational materials science

Abstract:Computational materials science has traditionally delegated algorithmic tasks to computers while leaving scientific judgments to humans. We argue that recent LLM-based agent harnesses enable an emerging form of scientific software, agentic programs, that combine deterministic algorithms with bounded LLM-based judgment, task-specific verification, episodic maturation, and complete delegation in production. We illustrate this concept with DeMARS, an agentic program for constructing atomistic models from experimentally measured disordered crystal structures.

Materials Science (cond-mat.mtrl-sci); Artificial Intelligence (cs.AI)

arXiv:2609.00795 [cond-mat.mtrl-sci]

(or arXiv:2609.00795v1 [cond-mat.mtrl-sci] for this version)

https://doi.org/10.48550/arXiv.2609.00795 Focus to learn more arXiv-issued DOI via DataCite (pending registration)

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.