收录解读
这篇论文把 agentic scientific discovery 从单体 agent 推向可组合的 atomistic research skill harness。
核心贡献是把材料、化学和药物发现中的工具、模拟器、数据库和分析流程组织成可插拔技能层,让通用 coding agent 能复用这些能力执行多阶段科学工作流。
它值得收录,因为这是 AI 科学工作流基础设施,而不只是某个单点预测模型。
局限在于当前证据主要来自预印本实验与作者自建评测,后续需要独立复现和更大范围部署验证。
原始摘要与中文对照
中文对照翻译
计算材料科学和化学涵盖了广阔的知识领域和碎片化的软件生态系统。尽管大型语言模型(LLMs)已展现出研究能力,但将单一智能体扩展以管理原子级研究的严谨性和复杂性仍然是一个挑战。在此,我们引入了AtomisticSkills,一个开源的衔接框架,它使通用AI编码智能体能够进行跨材料科学、化学和药物发现领域的原子级研究。通过将科学工作流分层分解为智能体技能和工具,AtomisticSkills为智能体提供了模块化、可扩展和即插即用的研究能力。该框架集成了100多种人工策划的多学科技能,包括数据库访问、热力学和动力学建模,以及采用机器学习原子间势(MLIPs)和密度泛函理论(DFT)的各种模拟引擎。我们根据科学文献验证了其功能覆盖范围,并展示了其在各种科学活动中的强大编排能力:锂离子固态电解质的生成设计、用于CO2捕获的金属有机框架的高通量筛选、自主MLIP基准测试和微调、用于药物设计的多阶段基于结构的虚拟筛选、多模态X射线衍射图谱分析,以及用于析氧反应的铁氧化物催化剂筛选。AtomisticSkills为构建完全自主的AI科学家提供了关键的智能体基础设施。
原始摘要
Computational materials science and chemistry span vast knowledge domains and fractured software ecosystems. Although large language models (LLMs) have demonstrated research capabilities, scaling monolithic agents to manage the rigor and complexity of atomistic research remains a challenge. Here, we introduce AtomisticSkills, an open-source harness framework that empowers general-purpose AI coding agents to conduct atomistic research across materials science, chemistry, and drug discovery. By hierarchically decomposing scientific workflows into agent skills and tools, AtomisticSkills provides agents with modular, extensible, and plug-and-play research capabilities. The framework integrates more than 100 human-curated multidisciplinary skills, including database access, thermodynamics and kinetics modeling, and diverse simulation engines employing machine learning interatomic potentials (MLIPs) and density functional theory (DFT). We validate its functional coverage against scientific literature and demonstrate robust orchestration capabilities across diverse scientific campaigns: generative design of Li-ion solid-state electrolytes, high-throughput screening of metal-organic frameworks for CO2 capture, autonomous MLIP benchmarking and finetuning, multi-stage structure-based virtual screening for drug design, multimodal X-ray diffraction pattern analysis, and screening of Fe-oxide catalysts for oxygen evolution reaction. AtomisticSkills provides a critical agent infrastructure towards building fully autonomous AI scientists.