arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.00185cond-mat.mtrl-scics.AI
收藏

QUASAR:一个通用的自主系统用于原子模拟及其能力的基准测试

QUASAR: A Universal Autonomous System for Atomistic Simulation and a Benchmark of Its Capabilities

School of Physics, Chemistry and Earth Sciences, Adelaide University(阿德莱德大学物理、化学与地球科学学院)

Fengxu Yang, Jack D. Evans

AI总结:

QUASAR通过整合多种原子模拟方法,实现自主的多尺度工作流,展示了其在材料筛选和新型材料评估中的应用潜力。

摘要:

QUASAR通过整合大型语言模型(LLMs)进入材料科学,为计算工作流程的优化提供了变革性机会,但当前代理系统仍受限于僵化的、精心设计的领域特定工具调用范式和狭窄的代理范围。在本工作中,我们介绍了QUASAR,一个通用的自主系统,用于原子模拟,旨在促进生产级的科学发现。QUASAR能够自主协调跨多种方法的复杂多尺度工作流程,包括密度泛函理论、机器学习势能、分子动力学和蒙特卡洛模拟。该系统包含强大的自适应规划、上下文高效内存管理和混合知识检索机制,以在无需人工干预的情况下导航现实研究场景。我们对QUASAR进行了三项三级任务的基准测试,从常规任务到前沿研究挑战,如光催化剂筛选和新型材料评估。这些结果表明,QUASAR可以作为通用的原子推理系统,而不是特定任务的自动化框架。它们还提供了初步证据,支持将代理AI作为计算化学研究工作流程组件的潜在部署,同时识别了需要进一步发展的领域。

英文摘要:

The integration of large language models (LLMs) into materials science offers a transformative opportunity to streamline computational workflows, yet current agentic systems remain constrained by rigid, carefully crafted domain-specific tool-calling paradigms and narrowly scoped agents. In this work, we introduce QUASAR, a universal autonomous system for atomistic simulation designed to facilitate production-grade scientific discovery. QUASAR autonomously orchestrates complex multi-scale workflows across diverse methods, including density functional theory, machine learning potentials, molecular dynamics, and Monte Carlo simulations. The system incorporates robust mechanisms for adaptive planning, context-efficient memory management, and hybrid knowledge retrieval to navigate real-world research scenarios without human intervention. We benchmark QUASAR against a series of three-tiered tasks, progressing from routine tasks to frontier research challenges such as photocatalyst screening and novel material assessment. These results suggest that QUASAR can function as a general atomistic reasoning system rather than a task-specific automation framework. They also provide initial evidence supporting the potential deployment of agentic AI as a component of computational chemistry research workflows, while identifying areas requiring further development.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑