FermiLink: An Agent Harness for Multidomain Scientific Simulations
- 9 November 2026
- journal article
- Published by American Chemical Society (ACS) in Journal of Chemical Theory and Computation
Abstract
Artificial intelligence (AI) agent harnesses have been developed for autonomous scientific simulations, but most current agent harnesses are tested on a single or a small set of software packages. Herein, FermiLink, an extensible open-source agent harness, is introduced for multidomain scientific simulations. Its key design principle is the separation of package knowledge bases from simulation workflows, so that simulation workflows in FermiLink, from figure-level simulations to full-paper-level research on high-performance computing clusters, operate uniformly among supported packages via a four-layer progressive disclosure mechanism. This agent harness is specifically optimized for high-performance computing (HPC) clusters, enabling multiday, multistep scientific simulations in the absence of human intervention. Using OpenAI Codex as the agent provider, the capabilities of FermiLink are demonstrated across approximately 50 scientific software packages spanning nine research domains from chemistry to engineering. Systematic benchmarks on 132 real-world figure-level reproduction tasks with 44 packages show that FermiLink reproduces 74 (56.1%) of published figures with simulations, among which 30 (22.7%) achieve high-fidelity agreement and 35 reach qualitative agreement with the target figures. A smaller set of human expert-guided reproduction benchmarks with 10 packages in physics and chemistry further highlights the importance of expert insights for improving the simulation fidelity. Beyond reproduction, a single-blinded study demonstrates that FermiLink can produce research-grade results on unpublished polariton physics problems when provided with sufficiently detailed research objectives. Overall, FermiLink provides a scalable research infrastructure that may accelerate the path from scientific questions to computational results across diverse domains.Keywords
Funding Information
- Division of Chemistry (2502758)
- Division of Chemistry (2620630)
- Chemical Sciences, Geosciences, and Biosciences Division (FWP 85666)
- Division of Materials Research (2500816)
This publication has 43 references indexed in Scilit:
- El Agente: An autonomous agent for quantum chemistryMatter, 2025
- Understanding Polaritonic Chemistry from Ab Initio Quantum ElectrodynamicsChemical Reviews, 2023
- Theoretical Advances in Polariton Chemistry and Molecular Cavity Quantum ElectrodynamicsChemical Reviews, 2023
- Reaction Mechanism Generator v3.0: Advances in Automatic Mechanism GenerationJournal of Chemical Information and Modeling, 2021
- NESSi: The Non-Equilibrium Systems Simulation packageComputer Physics Communications, 2020
- Bloch surface eigenstates within the radiation continuumLight: Science & Applications, 2013
- Singular characteristics and unique chemical bond activation mechanisms of photocatalytic reactions on plasmonic nanostructuresNature Materials, 2012
- QuTiP: An open-source Python framework for the dynamics of open quantum systemsComputer Physics Communications, 2012
- Meep: A flexible free-software package for electromagnetic simulations by the FDTD methodComputer Physics Communications, 2010
- Fast Parallel Algorithms for Short-Range Molecular DynamicsJournal of Computational Physics, 1995