🤖 AI Summary
本文提出了一种基于LLM的新型科学软件——代理程序,通过结合确定性算法与有限判断、任务验证及成熟过程,以解决计算材料科学中算法任务与科学判断分离的问题。
📝 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.