LQCDMaster: Agentic Scientific Computing for Lattice Quantum Chromodynamics Research

Source

• Source name: arXiv
• Source kind: paper
• Authors / organization: Haofei Gao, Tingjia Miao, Wenkai Jin, Muhua Zhang, Hanzhang Wang, Jie Ran, Jinxin Tan, Zhentao Zhang, Bo Tang, Leiyi Li, Jun Hua, Xiangyu Jiang, Qi-An Zhang, Siheng Chen, Wei Wang
• Venue: arXiv: hep-lat
• Published: 2026-07-16
• Collected: 2026-07-17
• URL: http://arxiv.org/abs/2607.15001v1
• PDF: https://arxiv.org/pdf/2607.15001v1
• DOI: UNKNOWN

Plain-Language Brief

The paper introduces LQCDMaster, a tool that automates the conversion of natural language Lattice Quantum Chromodynamics (LQCD) research tasks into executable PyQUDA computing workflows. The system generates workflows for various observables and reduces implementation time significantly while preserving end-to-end numerical validation. It has been evaluated on a benchmark with 70 tasks, where it reproduced expert-written implementations in 63 of the tasks at machine precision.

What the Document Says

• The paper presents LQCDMaster, a tool that converts natural language Lattice Quantum Chromodynamics (LQCD) research tasks into executable PyQUDA computing workflows
• The system combines agentic planning, expert-annotated LQCD skills and a deterministic Wick-contraction tool to generate measurement scripts, job-submission artifacts, execution logs, and numerical outputs.
• LQCDMaster was evaluated on a benchmark with 70 tasks, covering local and nonlocal two-point functions, Wilson loops, meson and baryon three-point functions.
• The generated workflows exactly reproduced expert-written implementations in 63 of the 70 tasks at machine precision.
• Three discrepancies were found in the remaining tasks due to convention mismatches.

Key Concepts Mentioned

• Lattice Quantum Chromodynamics (LQCD)
• scientific computing
• PyQUDA
• agentic planning
• Wick-contraction

Claims Made by the Document

• LQCDMaster can convert natural language LQCD research tasks into executable PyQUDA workflows.
• LQCDMaster reduces implementation time significantly while preserving end-to-end numerical validation.

Evidence Used

• The description of the tool and its components
• The evaluation results on the benchmark with 70 tasks

Methods / Approach

UNKNOWN

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

UNKNOWN

Open Questions

UNKNOWN

Notes for Future Q&A

May include interpretation. Labeled where it does.

UNKNOWN

Raw Abstract / Excerpt

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.