发表机构
School of Physics and Astronomy; Tsung-Dao Lee Institute; State Key Laboratory of Dark Matter Physics; School of Artificial Intelligence; Zhiyuan College; School of Physics; SciLand; Institute of Quantum Matter; Department of Physics（物理与天文学院; 李政道研究所; 暗物质物理国家重点实验室; 人工智能学院; 智远学院; 物理学院; SciLand; 量子物质研究所; 物理系）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对格点量子色动力学研究实际应用受限问题，提出LQCDMaster智能体，结合智能规划等技术将自然语言任务转化为计算工作流程。经实验评估，其能精确再现多数任务，大幅缩短实现时间，开创智能科学计算范式，促进相关研究。
AI 中文摘要
格点量子色动力学（LQCD）为计算强子可观测量提供了第一性原理框架，但其实际应用因将研究动机转化为可靠计算工作流程所需的大量专业知识而受限。本文介绍了LQCDMaster，这是一种工具增强、技能引导和领域专业化的科学计算智能体，可将自然语言的LQCD研究任务转换为可执行的PyQUDA计算工作流程，包括测量脚本、作业提交工件、执行日志和数值输出。该系统结合了智能规划、专家注释的LQCD技能和确定性的维克收缩工具，以约束代码生成中代数上脆弱的组件。我们在一项前沿科学研究基准上评估了LQCDMaster，该基准包括70个LQCD计算任务，可观测量涵盖局部和非局部两点函数、威尔逊圈、介子和重子三点函数。生成的工作流程在70个任务中的63个任务中以机器精度精确再现了专家编写的实现，另外三个差异归因于约定不匹配。在代表性可观测量中，智能体将实现时间从数小时缩短至数分钟，同时保留端到端的数值验证。此外，我们展示了一个由LQCDMaster驱动的探索的典型案例：对角威尔逊线的光锥分布振幅的格点计算，这是一个用标准方法可获取但以前从未计算过的量，以及质子、氘核、氚核、超子、超氘核和超氚核的谱计算。这项工作通过自动化格点QCD研究中的端到端科学计算工作流程，开创了智能科学计算的范式，降低了其障碍，促进了非标准科学思想的探索和验证。
英文摘要
Lattice quantum chromodynamics (LQCD) provides a first-principles framework for computing hadronic observables, but its practical use remains limited by the substantial expertise required to turn research motivation into reliable computing workflows. Here we present \textsc{LQCDMaster}, a tool-augmented, skill-guided and domain-specialized scientific computing agent that converts natural-language LQCD research tasks into executable PyQUDA computing workflows, including measurement scripts, job-submission artifacts, execution logs and numerical outputs. The system combines agentic planning, expert-annotated LQCD skills and a deterministic Wick-contraction tool to constrain the algebraically fragile components of code generation. We evaluate \textsc{LQCDMaster} on a benchmark at the forefront of scientific research, comprising 70 LQCD computing tasks, with observables covering local and nonlocal two-point functions, Wilson loops, meson and baryon three-point functions. The generated workflows exactly reproduce expert-written implementations in 63 of 70 tasks at machine precision, with three additional discrepancies attributable to convention mismatches. Across representative observables, the agent reduces implementation time from hours to minutes while preserving end-to-end numerical validation. Further, we present a typical case of \textsc{LQCDMaster}-driven exploration: a lattice computation of light-cone distribution amplitudes with diagonal Wilson-line, a quantity accessible with standard methods but never before computed, and computation of the spectrum of proton, deuteron, triton, hyperon, hyperdeuteron and hypertriton. This work pioneers the paradigm of agentic scientific computing by automating the end-to-end scientific computing workflows in lattice QCD research, lowering its barrier and facilitating the exploration and verification of non-standard scientific ideas.
Comments17 pages, 4 figures
