Metraipolis › archive › dc_aa028f1aee65
ECAS: An Edge-Controlled Agentic System for Validation-Gated Scientific Application Execution — arXiv:2609.14211
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.14211
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T22:50:58.120Z
- SHA-256 of the archived text
013271b77cfcd4ec968b7cce59b7c8a8dff59f99f0080c25b85a9508f3f218c5- Stable URL of this page
https://metraipolis.com/documento/dc_aa028f1aee65
How to cite
ECAS: An Edge-Controlled Agentic System for Validation-Gated Scientific Application Execution — arXiv:2609.14211 — arXiv (en), https://arxiv.org/abs/2609.14211 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_aa028f1aee65 (Metraipolis archive dc_aa028f1aee65, sha256 013271b77cfcd4ec968b7cce59b7c8a8dff59f99f0080c25b85a9508f3f218c5)
BibTeX
@misc{dcaa028f1aee65,
title = {ECAS: An Edge-Controlled Agentic System for Validation-Gated Scientific Application Execution — arXiv:2609.14211},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.14211},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_aa028f1aee65; sha256 013271b77cfcd4ec968b7cce59b7c8a8dff59f99f0080c25b85a9508f3f218c5},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.14211. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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}ontrolled \textbf{A}gentic \textbf{S}ystem for closed-loop execution of scientific computing campaigns with limited human intervention. \textsc{ECAS} separates \emph{reasoning}, \emph{control}, and \emph{execution}: a cloud-hosted LLM proposes plans, artifacts, and repairs; a user-controlled edge agent retains credentials, workflow state, and execution authority while enforcing policy and resource constraints; and the HPC system computes. Its core mechanism is \emph{validation-gated execution}: generated artifacts pass static checks and small-scale validation, failures trigger repairs from sanitized execution feedback, and target-scale execution is permitted only after validation and policy checks pass. \textsc{ECAS} also draws on an edge-resident library of expert-distilled, site-specific skills that is never disclosed to the cloud. In preliminary experiments with three scientific applications on two production ALCF systems under six injected fault types, closed-loop repair improves application success from 0/6 to 6/6 over one-shot generation, validation gating prevents all three observed target-scale failures, and skill conditioning improves success from 4/6 to 6/6. These results show the feasibility of delegating adaptive reasoning to the cloud while retaining execution control at the edge.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-15 in cs.AI).
Categorie arXiv: Distributed, Parallel, and Cluster Computing (cs.DC) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.14211 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-15T22:29:03.637Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).