SOURCE-LINKED INTELLIGENCE

ECAS: An Edge-Controlled Agentic System for Validation-Gated Scientific Application Execution

arXiv · AI, language, vision and robotics · article · Sep 13, 2026 · UTC

Scientific applications increasingly rely on high-performance computing (HPC), yet translating a scientist's high-level goal into a correct target-scale execution remains brittle and labor-intensive. Large language model (LLM) agents promise to automate this, but two obstacles remain: granting a cloud-hosted model direct HPC access exposes credentials and execution authority, while withholding it demands continuous human supervision; and one-shot generation cannot adapt when generated artifacts fail in a site-specific HPC environment. We present \textsc{ECAS}, an \textbf{E}dge-\textbf{C}ontrol

Read original source ↗ Open in workspace

recordType

paper

region

Global