arXivDaily arXiv每日学术速递 周一至周五更新
​通知:联邦节假日调休:哥伦布日 / 原住民日(Columbus Day / Indigenous Peoples' Day),今日(13日)无更新。
arXiv 2604.01647cs.AI

探索环境数据管理的鲁棒多智能体工作流

Exploring Robust Multi-Agent Workflows for Environmental Data Management

Florida International University(佛罗里达国际大学)

Boyuan Guan, Jason Liu, Yanzhao Wu, Kiavash Bahreini

AI总结:

本文提出EnviSmart系统,通过知识架构和角色分离的多智能体设计提升环境数据管理的可靠性和效率,验证了多智能体工作流在处理复杂环境数据任务中的优势。

摘要:

将LLM驱动的智能体嵌入环境FAIR数据管理中具有吸引力 - 它们可以外部化操作知识并在异构数据和演变规范中扩展整理。然而,用概率工作流替代确定性组件会改变故障模式:LLM管道可能生成看似正确但错误的输出,这些输出通过表面检查后会传播到不可逆的操作,如DOI生成和公开发布。我们介绍了EnviSmart,一个部署在校园存储基础设施上的生产数据管理系统,用于环境研究。EnviSmart通过两种机制将可靠性视为架构属性:一种是三轨知识架构,将行为(治理约束)、领域知识(可检索上下文)和技能(工具使用程序)作为持久、相互关联的存档;另一种是角色分离的多智能体设计,其中确定性验证器和审计手工会在信任边界前恢复故障停止语义,防止不可逆步骤。我们比较了两种生产部署。大学的GIS中心生态档案(849个整理数据集)作为单智能体基准。SF2Bench,一个包含2,452个监测站和8,557个已发布文件的复合洪水基准,涵盖了39年的数据,验证了多智能体工作流。多智能体方法提高了效率 - 单个操作员在两天内完成,通过跨部署的重复存档重用;并且可靠性:审计手工会在发布前检测并阻止影响所有2,452个站点的坐标转换错误。一个代表性事件(ISS-004)展示了基于边界的限制,具有10分钟的检测延迟,零用户暴露和80分钟的解决时间。本文已被接受于PEARC 2026。

英文摘要:

Embedding LLM-driven agents into environmental FAIR data management is compelling - they can externalize operational knowledge and scale curation across heterogeneous data and evolving conventions. However, replacing deterministic components with probabilistic workflows changes the failure mode: LLM pipelines may generate plausible but incorrect outputs that pass superficial checks and propagate into irreversible actions such as DOI minting and public release. We introduce EnviSmart, a production data management system deployed on campus-wide storage infrastructure for environmental research. EnviSmart treats reliability as an architectural property through two mechanisms: a three-track knowledge architecture that externalizes behaviors (governance constraints), domain knowledge (retrievable context), and skills (tool-using procedures) as persistent, interlocking artifacts; and a role-separated multi-agent design where deterministic validators and audited handoffs restore fail-stop semantics at trust boundaries before irreversible steps. We compare two production deployments. The University's GIS Center Ecological Archive (849 curated datasets) serves as a single-agent baseline. SF2Bench, a compound flooding benchmark comprising 2,452 monitoring stations and 8,557 published files spanning 39 years, validates the multi-agent workflow. The multi-agent approach improved both efficiency - completed by a single operator in two days with repeated artifact reuse across deployments - and reliability: audited handoffs detected and blocked a coordinate transformation error affecting all 2,452 stations before publication. A representative incident (ISS-004) demonstrated boundary-based containment with 10-minute detection latency, zero user exposure, and 80-minute resolution. This paper has been accepted at PEARC 2026.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑