arXiv cs.AI· Muhammad Ashfaq, Ahmed R. Sadik, Ewan Warburton, Pyry Kotilainen, Niko M\"akitalo, Tommi Mikkonen·· 3 小时前AI 评分33
SafeOrchestrate：面向信息物理系统的运行时校验、意图驱动的编排架构
SafeOrchestrate: Runtime Checked Intent-Driven Orchestration for Cyber-Physical Systems
AI 导读
研究者提出 SafeOrchestrate，一种运行时校验、意图驱动的信息物理系统（CPS）编排参考架构。它从自然语言意图生成 LTL 风格规约，经由 MCP 接入 WoT Thing Description 设备能力，并以 SMT 检查每个候选动作。
正文 · 原文
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, but unconstrained large language model (LLM) tool use is risky because actions must respect device capabilities, runtime state, and safety constraints. We present Safe Orchestrate, a reference architecture for runtime checked, intent driven CPS orchestration. Given an NL intent, it derives atomic goals, generates a runtime checkable specification for each, grounds the specifications to device affordances, and verifies every candidate action against runtime state and safety constraints before execution. In a Web of Things (WoT) instantiation, the architecture produces Linear Temporal Logic (LTL) style specifications from the NL intent, grounds them to Thing Description (TD) affordances exposed through the Model Context Protocol (MCP), and checks candidate actions against satisfiability modulo theories (SMT) backed guardrails. We evaluate this instantiation on simulated smart home, greenhouse, and industrial automation tasks against a direct LLM to MCP baseline. Safe Orchestrate maintains 100% required action accuracy on every task and 100% MCP Execution Similarity (MCP ES) on all but one, where MCP ES is 92%. By contrast, the baseline degrades on multi device, event triggered, and ordered tasks, with MCP ES falling to 13%. These results suggest that combining LLM based specification generation with role aware grounding and runtime constraint checking improves reliability for open CPS orchestration without enriched TD annotations or planning domain expertise.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.09364 [cs.AI] |
| (or arXiv:2611.09364v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.09364 arXiv-issued DOI via DataCite |
Submission history
From: Ahmed R. Sadik Dr.-Ing. [view email]
[v1]
Fri, 6 Nov 2026 12:03:02 UTC (123 KB)
[v2]
Wed, 11 Nov 2026 08:55:00 UTC (125 KB)
来源：arXiv cs.AI · arxiv.org