The plant phenotyping workflow of the Orchestrated Platform for Autonomous Laboratories is explored, which couples Oak Ridge National Laboratory's Advanced Plant Phenotyping Laboratory with the Frontier supercomputer and replaces roughly twelve hours of manual analysis with interactive queries returning in seconds to minutes.
Abstract
Autonomous, cross-facility science requires capabilities that no individual project should have to build for itself: managed execution for long-lived services, versioned distribution of models to remote compute systems, governed access to large language models, a shared substrate for experimental data, and end-to-end provenance. The U.S. Department of Energy Genesis Mission platform, delivered through the American Science Cloud, provides these as reusable services. This paper reports how the Genesis platform enables cross-facility experiments and accelerates scientific discovery. We explore the plant phenotyping workflow of the Orchestrated Platform for Autonomous Laboratories as the exemplar: it couples Oak Ridge National Laboratory's Advanced Plant Phenotyping Laboratory with the Frontier supercomputer. In a 40-day nickel-treatment campaign, the resulting workflow replaced roughly twelve hours of manual analysis with interactive queries returning in seconds to minutes.
The results suggest that integrating persistent execution with session-level provenance can improve the reliability of AI-assisted scientific workflows, and recommend that integrating persistent execution with session-level provenance can improve the reliability of AI-assisted scientific workflows.
Gong-Bo Zhang, Hao Li, Yu Wang et al.· 0 citations
HPC-AutoResearch is presented, a proof-of-concept system for the autonomous execution of compiled-code research workflows in HPC-like environments that divides this sub-pipeline into five phases—planning, environment setup, coding, compilation, and execution—localizing failures within each phase and enabling iterative...
T. Kotama, Shun-ichiro Hayashi, Daichi Mukunoki et al.· 1 citation
HEPToolBench is introduced, a benchmark of 28 collider-simulation tasks scored by deterministic, task-specific scorers, plus a three-task structured-debugging extension, and moving syntax generation into deterministic software can substantially improve reliability for both small local and frontier models.
High-throughput and autonomous experimentation generate complex, heterogeneous datasets whose reuse, large-scale analysis, and linking to data from first-principles calculations remain challenging. Here, we report on an operational deployment of the open-source NOMAD Oasis data infrastructure as a digital backbone for...
Lena A. Mittmann, Hampus Nässtrom, Eugène Bertin et al.· Faraday discussions· 0 citations
An extension and comprehensive real-world validation of Co-Scientist, a Gemini-based multi-agent system designed to accelerate end-to-end scientific research across hypothesis generation, experimentation, and manuscript generation, demonstrates progress toward closed-loop multi-agent scientific AI systems capable of ac...
Samuel Schmidgall, Xiao-Kai Zhu, Marian Shaw et al.· 2 citations
The integration combines DAGonStar’s orchestration capabilities with CAPIO’s efficient data handling to better support workflows operating on continuous or large-scale datasets and improves the responsiveness and flexibility of scientific workflows.
Simone Perrotta, G. de Vita, Gennaro Mellone et al.· 0 citations