Adnan KhanAdnanProduct & AI
San Francisco Bay Area
Get in touch

Source note3 min read

An Agentic Workflow for Legacy HPC Modernization: Converting the Two-Electron-Integral Core of GAMESS

Source

arXiv

arxiv.org/abs/2608.12249v1

Read the source

Source

  • Source name: arXiv
  • Source kind: paper
  • Authors / organization: Yuzhong Shen, Masha Sosonkina, Peng Xu, Mark S. Gordon
  • Venue: arXiv: cs.AI
  • Published: 2026-08-12
  • Collected: 2026-08-13
  • URL: http://arxiv.org/abs/2608.12249v1
  • PDF: https://arxiv.org/pdf/2608.12249v1
  • DOI: UNKNOWN
  • Registry group: academic_apis_and_preprints
  • Evidence role: canonical_academic_index
  • Language: en
  • Country / region: UNKNOWN

Plain-Language Brief

Researchers proposed an agentic workflow to modernize legacy Fortran code at a large scale. They applied this method in a case study by converting parts of GAMESS, a quantum-chemistry software package, from Fortran 77 to Fortran 2008. The converted code passed various tests and showed no chemistry-relevant differences.

What the Document Says

  • The authors propose an agentic workflow for modernizing large-scale legacy Fortran code.
  • The proposed workflow involves three prompt-specialized agents operating under a version-controlled specification, with humans holding a small number of gates.
  • The safety of the arrangement is ensured by an exact verification oracle inherited from the domain.
  • The boundary of safe delegation lies exactly where the oracle stops seeing.
  • The authors apply this workflow in a case study to convert parts of GAMESS from Fortran 77 to Fortran 2008.
  • The scope of conversion was twelve source files, 56,448 lines, and 225 subroutines for computing electron repulsion integrals.
  • The agents ran as three Claude Code roles in isolated worktrees.
  • The work spanned four Claude model generations.
  • Since GAMESS ships a standard test suite with canonical printed energies, the authors used bit-for-bit reproduction of those energies as the merge criterion.
  • All twelve source files passed a 51-test validation battery consisting of the 49 standard GAMESS tests and two additional calculations.
  • Across 612 test runs, there were no chemistry-relevant differences.
  • Every file also passed the Jenkins tests used for continuous integration.

Key Concepts Mentioned

  • legacy Fortran modernization
  • agentic workflow
  • GAMESS
  • quantum-chemistry
  • Fortran 77
  • Fortran 2008
  • electron repulsion integrals
  • verification oracle
  • Claude Code roles
  • isolated worktrees

Claims Made by the Document

  • The proposed agentic workflow can modernize large-scale legacy Fortran code at a production scale.

Evidence Used

  • The application of the proposed workflow in converting GAMESS from Fortran 77 to Fortran 2008 and the successful passing of various tests.

Methods / Approach

  • Using an agentic workflow involving prompt-specialized agents, version control, exact verification oracle, and isolated worktrees

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

Modernizing legacy Fortran is a problem of volume: the transformations are individually routine, but the codebases can be enormous, and across much of computational science the work simply goes undone. We propose an agentic workflow that takes this work on at production scale, and we set out to measure how far such delegation can reach. In this work, three prompt-specialized agent roles operate under a version-controlled specification that the agents themselves authored and revised, while humans hold a small number of gates. The arrangement is kept safe by an exact verification oracle inherited from the domain, and the boundary of safe delegation lies exactly where that oracle stops seeing. We apply the proposed workflow in a case study, converting the two-electron-integral routines of GAMESS (General Atomic and Molecular Electronic Structure System), a mature quantum-chemistry package with a 48-year development history, from fixed-form Fortran 77 to free-form Fortran 2008. The scope of this work was twelve source files, 56,448 lines, and 225 subroutines for computing electron repulsion integrals. The agents ran as three Claude Code roles in isolated worktrees, and the work spanned four Claude model generations. Because the GAMESS group ships a standard test suite whose printed energies its user community treats as canonical, we could adopt bit-for-bit reproduction of those energies as the merge criterion, where a deviation in the twelfth decimal place counts as a failure rather than drift. All twelve source files pass a 51-test validation battery comprising the 49 standard GAMESS tests and two additional calculations, and across 612 test runs the number of chemistry-relevant differences is zero, and every file also passes the Jenkins tests that are used for continuous integration.