English(EN) SafeOrchestrate: Runtime Checked Intent-Driven Orchestration for Cyber-Physical Systems

新架构增强了物理信息系统的LLM编排

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-14 05:00

研究人员开发了SafeOrchestrate，这是一种新颖的架构，旨在通过自然语言意图增强物理信息系统（CPS）编排的可靠性。该系统从用户意图生成运行时可检查的规范，将这些规范与设备功能进行关联，并在执行前根据运行时状态和安全约束验证操作。在模拟的智能家居和工业自动化任务上的评估表明，SafeOrchestrate实现了100%的必要操作准确率，显著优于基线直接LLM方法，后者在复杂任务上的性能大幅下降。 AI

影响增强了LLM驱动的物理系统控制的可靠性，有可能在复杂环境中实现更安全的自动化。

排序理由详细介绍新架构及其评估的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 16 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 详细介绍新架构及其评估的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, product; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Muhammad Ashfaq, Ahmed R. Sadik, Ewan Warburton, Pyry Kotilainen, Niko M\"akitalo, Tommi Mikkonen · 2026-11-14 05:00

SafeOrchestrate：面向网络物理系统的运行时检查意图驱动编排

arXiv:2611.09364v2 Announce Type: replace Abstract: Modern cyber physical systems (CPS) integrate heterogeneous sensors, actuators, controllers, and services, composed at runtime rather than at design time. Orchestrating such systems through natural language (NL) is attractive, b…

本文如何被排名

报道来源 [1]

SafeOrchestrate：面向网络物理系统的运行时检查意图驱动编排

相关实体

相关话题