Agent-E2MD：将原子间势方程自主翻译为LAMMPS中经物理验证的pair style

中文摘要 AI 辅助

原子间势是分子动力学（MD）的基础，决定了金属、半导体、氧化物、液体和反应性体系等预测性原子级模型的保真度。一个势函数只有在生产级MD代码中可靠实现后才具有实际价值。缓慢且需要专业知识的实现过程不仅仅是方程到C++的翻译：它必须选择邻居列表架构，评估和分配多体导数，管理处理器间通信，并保持宿主代码的能量、力和维里约定。我们提出了Agent-E2MD，一种知识引导的智能体工作流，可将用户指定的原子间模型翻译为可执行的LAMMPS pair style。它结合了架构分类、代码生成、自主构建-测试-修复循环、模拟执行和分层物理验证。我们在七种材料-势组合上测试了Agent-E2MD：Lennard-Jones氩、EAM/FS银、MEAM铋、Tersoff硅、GAP镍、ReaxFF C/H/N/O，以及一个最近开发的用于铝的符号回归EAM（Symb EAM）模型，该模型目前在LAMMPS中不可用。单点结果与所有七个模型的参考能量和力匹配。五个晶体多体基准恢复了参考的弛豫晶格性质、空位形成能和弹性常数。银、铋、硅和镍在纳秒尺度模拟的有限温度下是稳定的；ReaxFF将验证扩展到具有演化键级和电荷平衡的反应动力学。结果表明，原子间势的软件架构可以从其物理和数学结构中推断出来。Agent-E2MD并不取代科学判断；它将用户的精力从常规实现转移到模型定义、严格验证和物理解释上。该框架为新兴的AI驱动的势函数发现方法和生产规模原子级模拟之间提供了一座实用、可追溯的桥梁。

英文摘要

Interatomic potentials underpin MD and govern predictive atomistic-model fidelity for metals, semiconductors, oxides, liquids, and reactive systems. A potential has limited practical value until reliably implemented in production MD code. Slow, expertise-intensive implementation requires more than equation-to-C++ translation: it must select the neighbor-list architecture, evaluate and distribute many-body derivatives, manage interprocessor communication, and preserve host-code energy, force, and virial conventions. We introduce Agent-E2MD, a knowledge-guided agentic workflow that translates user-specified interatomic models into executable LAMMPS pair styles. It combines architectural classification, code generation, autonomous build-test-fix cycles, simulation execution, and hierarchical physical validation. We test Agent-E2MD on seven material-potential pairs: Lennard--Jones Ar, EAM/FS Ag, MEAM Bi, Tersoff Si, GAP Ni, ReaxFF C/H/N/O, and a recently developed Symbolic Regression EAM (Symb EAM) model for Al, currently unavailable in LAMMPS. Single-point results match reference energies and forces for all seven models. Five crystalline many-body benchmarks recover reference relaxed lattice properties, vacancy formation energies, and elastic constants. Ag, Bi, Si, and Ni are stable at finite temperature in nanosecond-scale simulations; ReaxFF extends validation to reactive dynamics with evolving bond order and charge equilibration. Results demonstrate that the software architecture for an interatomic potential can be inferred from its physical and mathematical structure. Agent-E2MD does not replace scientific judgment; it shifts users' effort from routine implementation to model definition, rigorous validation, and physical interpretation. The framework provides a practical, traceable bridge between emerging AI-driven potential discovery methods and production-scale atomistic simulations.

发表机构

• University of Illinois Chicago（伊利诺伊大学芝加哥分校）
• Center for Nanoscale Materials, Argonne National Laboratory（阿贡国家实验室纳米材料中心）

机构由 AI 辅助整理，请以论文原文为准。