Back to AI News
arxiv

SafeOrchestrate: Runtime-Checked Intent-Driven Orchestration for Cyber-Physical Systems

SafeOrchestrate is a reference architecture for intent-driven cyber-physical system orchestration that derives atomic goals from natural-language intents and generates runtime-checkable specifications. In a Web of Things instantiation, it produces LTL-style specifications, grounds them to Thing Description affordances via MCP, and verifies candidate actions with SMT-backed guardrails. On simulated smart-home, greenhouse, and industrial-automation tasks, it reports 100% required action accuracy and 100% MCP Execution Similarity on all but one task (92%), versus a direct LLM-to-MCP baseline that falls to 13% MCP ES on multi-device, event-triggered, and ordered tasks.

AI Brief

It presents a concrete architecture for making LLM-driven cyber-physical orchestration safer and more reliable through runtime-checked specifications and grounding.

arXiv:2611.09364v1 Announce Type: new 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.
Be the first to rate this article.

Comments & Questions (0)

Captcha
Please be respectful — let's keep the conversation friendly.

No comments yet

Be the first to comment!