Adnan KhanAdnanProduct & AI
San Francisco Bay Area
Get in touch

Source note3 min read

LQCDMaster: Agentic Scientific Computing for Lattice Quantum Chromodynamics Research

Source

arXiv

arxiv.org/abs/2607.15001v1

Read the source

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 authors present LQCDMaster, a tool that converts natural language Lattice Quantum Chromodynamics (LQCD) research tasks into executable Python scripts for computing workflows. The system reduces implementation time and reproduces expert-written implementations accurately. It was tested on 70 benchmark tasks and showed significant efficiency in reducing computation time while preserving numerical validation.

What the Document Says

  • The authors present a tool called LQCDMaster.
  • LQCDMaster converts natural language Lattice Quantum Chromodynamics (LQCD) research tasks into executable PyQUDA computing workflows.
  • The system includes measurement scripts, job-submission artifacts, execution logs, and numerical outputs.
  • It combines agentic planning, expert-annotated LQCD skills, and a deterministic Wick-contraction tool.
  • The authors evaluate LQCDMaster on a benchmark of 70 LQCD computing tasks.
  • The generated workflows exactly reproduce expert-written implementations in 63 out of 70 tasks at machine precision.
  • Three additional discrepancies are attributed to convention mismatches.
  • Across representative observables, the agent reduces implementation time from hours to minutes while preserving end-to-end numerical validation.
  • The authors present a case study of LQCDMaster-driven exploration: a lattice computation of light-cone distribution amplitudes with diagonal Wilson-line and the spectrum of various particles.
  • The work aims to automate 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.

Key Concepts Mentioned

  • LQCDMaster
  • Lattice Quantum Chromodynamics
  • PyQUDA
  • workflow automation
  • agentic planning
  • Wilson loops
  • meson and baryon three-point functions
  • light-cone distribution amplitudes

Claims Made by the Document

  • LQCDMaster can convert natural language research tasks into executable computing workflows.
  • LQCDMaster reproduces expert-written implementations accurately.
  • LQCDMaster reduces implementation time significantly.

Evidence Used

  • The authors present LQCDMaster
  • It combines agentic planning, expert-annotated LQCD skills, and a deterministic Wick-contraction tool
  • The generated workflows exactly reproduce expert-written implementations
  • Across representative observables, the agent reduces implementation time from hours to minutes

Methods / Approach

  • agentic planning
  • expert-annotated LQCD skills
  • deterministic Wick-contraction tool

Limitations Stated by the Authors

Three additional discrepancies are attributed to convention mismatches.

Limitations Noted by the Agent

Agent interpretation — not from the source.

The system may face challenges when encountering tasks with unconventional or undefined conventions.

Open Questions

  • What is the precision of LQCDMaster's implementations in the remaining 7 out of 70 tasks?
  • How does LQCDMaster handle tasks that deviate significantly from standard methods?

Notes for Future Q&A

May include interpretation. Labeled where it does.

It's important to note that the authors only mention discrepancies in three tasks. The precision of the implementation in the remaining tasks is not specified.

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.