Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.03460 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908945066491904 |
|---|---|
| author | Meng, Gang Vargas, Andres Felipe Bocanegra Ji, Xinwei Garcia-Gaitan, Federico Reyes-Osorio, Felipe Varela-Manjarres, Jalil Ren, Yafei Dinpajooh, Mohammadhasan Nikolić, Branislav K. Li, Tao E. |
| author_facet | Meng, Gang Vargas, Andres Felipe Bocanegra Ji, Xinwei Garcia-Gaitan, Federico Reyes-Osorio, Felipe Varela-Manjarres, Jalil Ren, Yafei Dinpajooh, Mohammadhasan Nikolić, Branislav K. Li, Tao E. |
| contents | Artificial-intelligence (AI) agent frameworks have been developed for autonomous scientific simulations, but most current agent frameworks are tailored to a single or a small set of software packages. Herein, FermiLink, a unified and extensible open-source agent framework 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. Using OpenAI Codex as the agent provider, the capabilities of FermiLink are demonstrated across approximately 50 scientific software packages spanning nine research domains from physics 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 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 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 Beyond reproduction, a single-blinded study demonstrates that FermiLink can produce research-grade results on unpublished polariton physics problems when provided with sufficiently detailed research objectives and source code, even in the absence of external documentation or tutorials. Overall, FermiLink provides a scalable research infrastructure that may accelerate the path from scientific questions to computational results across diverse domains. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_03460 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | FermiLink: A Unified Agent Framework for Multidomain Autonomous Scientific Simulations Meng, Gang Vargas, Andres Felipe Bocanegra Ji, Xinwei Garcia-Gaitan, Federico Reyes-Osorio, Felipe Varela-Manjarres, Jalil Ren, Yafei Dinpajooh, Mohammadhasan Nikolić, Branislav K. Li, Tao E. Chemical Physics Computational Physics Artificial-intelligence (AI) agent frameworks have been developed for autonomous scientific simulations, but most current agent frameworks are tailored to a single or a small set of software packages. Herein, FermiLink, a unified and extensible open-source agent framework 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. Using OpenAI Codex as the agent provider, the capabilities of FermiLink are demonstrated across approximately 50 scientific software packages spanning nine research domains from physics 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 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 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 and source code, even in the absence of external documentation or tutorials. Overall, FermiLink provides a scalable research infrastructure that may accelerate the path from scientific questions to computational results across diverse domains. |
| title | FermiLink: A Unified Agent Framework for Multidomain Autonomous Scientific Simulations |
| topic | Chemical Physics Computational Physics |
| url | https://arxiv.org/abs/2604.03460 |