Skip to content

Autonomous science campaigns

A systematic study running real physics, chemistry, and engineering campaigns end-to-end across ALCF, NERSC, and OLCF systems — not to produce a single result, but to examine how well an autonomous agent handles failure, self-corrects, and knows when a result is trustworthy, not just whether a job finished. Across the full study, agents self-corrected roughly 49 of 65 recorded iteration failures with zero human intervention.

  • Finding argon's melting point via molecular dynamics


    A 7-temperature LAMMPS sweep locates the solid-to-liquid transition within 4% of the literature value.

    Read the full campaign

  • Silicon's electronic band structure from first principles


    A four-step Quantum ESPRESSO DFT workflow computes silicon's band gap in 24 seconds on one GPU node.

    Read the full campaign

  • Trp-cage mini-protein thermal stability across three temperatures


    Three GROMACS runs show a mini-protein's structure destabilizing steadily as temperature climbs.

    Read the full campaign

  • Water dimer binding energy — DFT vs. quantum Monte Carlo


    A clean DFT result, plus an honestly reported handoff failure when refining it with quantum Monte Carlo.

    Read the full campaign

  • Turbulent pipe flow across two facilities: Polaris vs. Aurora


    The same CFD simulation on NVIDIA and Intel GPUs, five build iterations apart, within 13% throughput of each other.

    Read the full campaign

  • Reproducing the same GPU bug on two different supercomputers


    A cosmology code's GPU crash reproduced identically on Polaris and Perlmutter, confirming a real code defect.

    Read the full campaign

  • GROMACS water box: GPU (Polaris) vs. CPU-only (Frontier)


    A cross-facility performance baseline that later fed a follow-on GPU-porting effort on Frontier.

    Read the full campaign

  • Opening silicon's band gap the right way: G0W0 many-body corrections


    A many-body GW correction pushes silicon's DFT gap toward its true value, as theory predicts.

    Read the full campaign

  • Breaking a nitrogen molecule apart, three ways, across three supercomputers


    DMRG matches exact full configuration interaction to nine decimal places, verified on three systems.

    Read the full campaign

  • Copper's melting point via a heating-ramp simulation


    A continuous heating ramp finds copper's melting discontinuity, showing the expected superheating artifact.

    Read the full campaign

  • Pushing turbulent pipe flow to a higher Reynolds number


    The same spectral-element method holds stable and performant at nearly 4x the turbulence intensity.

    Read the full campaign

  • Running four molecular dynamics replicas at once


    Four independent GROMACS replicas in one job, each on its own GPU, with negligible parallel overhead.

    Read the full campaign

  • Silicon carbide's vibrational spectrum from first principles


    DFPT phonon frequencies land within 1% of experiment, with symmetry checks passing cleanly.

    Read the full campaign

  • Verifying HPC applications actually run


    A coverage sweep across ~38 applications and 9 systems, checking for a physically sensible result, not just a clean exit.

    Read the full campaign

← Back to Science Campaigns