An Agentic Workflow for Legacy HPC Modernization: Converting the Two-Electron-Integral Core of GAMESS
2026-08-12 • Artificial Intelligence
Artificial Intelligence
AI summaryⓘ
The authors tackled the challenge of updating very old Fortran code used in scientific computing, which is usually tedious due to its large size. They created a system where specialized AI agents automatically rewrite the code while humans oversee critical steps to ensure safety. They tested this approach on a big quantum chemistry program called GAMESS, successfully converting complex routines without any errors in test results. Their method maintained exact accuracy by comparing outputs down to tiny details, showing that AI can reliably handle large-scale code modernization in scientific software.
Fortran 77Fortran 2008GAMESSelectron repulsion integralscode modernizationAI agentssoftware verificationquantum chemistrytest suitecontinuous integration
Authors
Yuzhong Shen, Masha Sosonkina, Peng Xu, Mark S. Gordon
Abstract
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.