ThermoLLM uses a physics-informed spatial-semantic knowledge graph with LLMs for HVAC control in a five-zone EnergyPlus simulation and reports the best energy-comfort trade-off plus lowest PMV violations among tested methods.
Pre-trainedlargelanguage models for industrial control
5 Pith papers cite this work, alongside 8 external citations. Polarity classification is still indexing.
5
Pith papers citing it
8
external citations · external index
citation-role summary
background 1
citation-polarity summary
years
2026 5verdicts
UNVERDICTED 5roles
background 1polarities
background 1representative citing papers
An agentic LLM framework with multi-agent workflow, digital process plant twin, and Graph RAG on CPSMod ontology generates and validates fault recovery actions in simulation for discrete batch and continuous stirred-tank processes.
A tutorial framework for knowledge-grounded LLM agents as constrained planners for fault recovery in process plants, including validation strategies and open Python environments for two case studies.
A semantic framework uses a knowledge graph on modular alignment ontology plus constrained LLM to generate C&E logic, narratives, and SWRL rules, shown on a modular process plant with claimed reduction in manual effort.
The paper proposes a bidirectional continuum between LLMs and control systems, covering LLM-assisted controller design, control-based LLM steering, and state-space modeling of LLMs.
citing papers explorer
-
ThermoLLM: Thermodynamics-Aware HVAC Control with Spatial-Semantic Knowledge Graph
ThermoLLM uses a physics-informed spatial-semantic knowledge graph with LLMs for HVAC control in a five-zone EnergyPlus simulation and reports the best energy-comfort trade-off plus lowest PMV violations among tested methods.
-
From Detection to Action: Using LLM Agents for Fault-Tolerant Control
An agentic LLM framework with multi-agent workflow, digital process plant twin, and Graph RAG on CPSMod ontology generates and validates fault recovery actions in simulation for discrete batch and continuous stirred-tank processes.
-
A Tutorial on Autonomous Fault-Tolerant Control Using Knowledge-Grounded LLM Agents
A tutorial framework for knowledge-grounded LLM agents as constrained planners for fault recovery in process plants, including validation strategies and open Python environments for two case studies.
-
Automating Cause-Effect Specification with Knowledge Graphs and Large Language Models
A semantic framework uses a knowledge graph on modular alignment ontology plus constrained LLM to generate C&E logic, narratives, and SWRL rules, shown on a modular process plant with claimed reduction in manual effort.
-
When control meets large language models: From words to dynamics
The paper proposes a bidirectional continuum between LLMs and control systems, covering LLM-assisted controller design, control-based LLM steering, and state-space modeling of LLMs.