智能体程序:计算材料科学中一种新兴的科学软件形式
Agentic programs: an emerging form of scientific software in computational materials science
浏览论文内容
中文总结 AI 辅助
该研究提出计算材料科学中新兴的智能体程序,结合确定性算法与LLM判断等特性,以DeMARS为例说明其可用于从实验无序晶体结构构建原子模型。
中文摘要 AI 辅助
计算材料科学传统上会将算法任务委派给计算机,而将科学判断留给人类。我们认为,近期基于大语言模型(LLM)的智能体技术催生了一种新兴的科学软件形式——智能体程序,它将确定性算法与受限的LLM判断、任务特定验证、阶段性成熟机制,以及生产环境中的完全委派能力相结合。我们以DeMARS为例阐释这一概念,DeMARS是一款用于从实验测量的无序晶体结构构建原子模型的智能体程序。
英文摘要
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.
发表机构
- Research Institute of Advanced Materials, Seoul National University(首尔国立大学先进材料研究所)
- Department of Materials Science and Engineering, Seoul National University(首尔国立大学材料科学与工程系)
- Center for AI and Natural Sciences, Korea Institute for Advanced Study(韩国高等研究院人工智能与自然科学中心)
机构由 AI 辅助整理,请以论文原文为准。