Large Language Models for Control
By: Adil Rasheed, Oscar Ravik, Omer San
Potential Business Impact:
Lets computers control machines without engineers.
This paper investigates using large language models (LLMs) to generate control actions directly, without requiring control-engineering expertise or hand-tuned algorithms. We implement several variants: (i) prompt-only, (ii) tool-assisted with access to historical data, and (iii) prediction-assisted using learned or simple models to score candidate actions. We compare them on tracking accuracy and actuation effort, with and without a prompt that requests lower actuator usage. Results show prompt-only LLMs already produce viable control, while tool-augmented versions adapt better to changing objectives but can be more sensitive to constraints, supporting LLM-in-the-loop control for evolving cyber-physical systems today and operator and human inputs.
Similar Papers
Linear Feedback Control Systems for Iterative Prompt Optimization in Large Language Models
Machine Learning (CS)
Makes AI understand what you want better.
From Language to Action: A Review of Large Language Models as Autonomous Agents and Tool Users
Computation and Language
AI learns to think, plan, and improve itself.
LLMPC: Large Language Model Predictive Control
Artificial Intelligence
Makes computers plan better using smart instructions.