智能体
arxiv.org ·
ECAS：用于验证门控科学应用执行的边缘控制智能体系统
该论文提出 ECAS，一种边缘控制的智能体系统，用于科学计算任务的闭环执行。系统将推理、控制与执行分离：云端 LLM 负责提出计划、生成产物与修复方案，用户侧边缘智能体保留凭证、工作流状态与执行权限并执行策略和资源约束，HPC 系统负责计算。核心机制为验证门控执行：生成产物先通过静态检查与小规模验证，失败时基于脱敏执行反馈触发修复，只有验证与策略检查通过后才允许目标规模执行；边缘侧还维护不向云端披露的专家蒸馏站点技能库。在 ALCF 两套生产系统、三类科学应用、六种注入故障的初步实验中，闭环修复将应用成功率从 0/6 提升至 6/6，验证门控阻止了全部三例观察到的目标规模失败，技能条件化将成功率从 4/6 提升至 6/6。
AI推荐理由 arXiv 预印本，作者与摘要信息完整，事实明确、信息密度高。核心新信息是 ECAS 将 LLM 推理、边缘控制与 HPC 执行分离，并以 validation-gated execution 机制在验证与策略检查通过后才允许目标规模执行；初步实验在 ALCF 两套生产系统、三类科学应用、六种注入故障下，闭环修复把成功率从 0/6 提升到 6/6，验证门控阻止了全部三例目标规模失败，技能条件化把成功率从 4/6 提升到 6/6。局限是仅为初步实验、样本量小、尚未见同行评审或独立复现，且摘要未给出延迟、成本与安全性的量化评估。
78
正文
Computer Science > Distributed, Parallel, and Cluster Computing
arXiv:2609.14211 (cs)
[Submitted on 13 Sep 2026]
Title:ECAS: An Edge-Controlled Agentic System for Validation-Gated Scientific Application Execution
Authors:Baixi Sun, Mingze Xia, Huihuo Zheng
View a PDF of the paper titled ECAS: An Edge-Controlled Agentic System for Validation-Gated Scientific Application Execution, by Baixi Sun and 2 other authors
View PDF
HTML (experimental)
Abstract: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.
Subjects:
Distributed, Parallel, and Cluster Computing (cs.DC); Artificial Intelligence (cs.AI)
Cite as:
arXiv:2609.14211 [cs.DC]
(or
arXiv:2609.14211v1 [cs.DC] for this version)
https://doi.org/10.48550/arXiv.2609.14211
Focus to learn more
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Baixi Sun [view email]
[v1]
Sun, 13 Sep 2026 00:41:19 UTC (2,500 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled ECAS: An Edge-Controlled Agentic System for Validation-Gated Scientific Application Execution, by Baixi Sun and 2 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.DC
new
|
recent
| 2026-09
Change to browse by:
cs
cs.AI
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
export BibTeX citation
Loading...
BibTeX formatted citation
×
loading...
Data provided by:
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? |
Disable MathJax (What is MathJax?)