Large Language Models for Control

2025/11/01 by Adil Rasheed, Rasheed, Adil, Oscar Ravik +3 · 1 citation
Computer Science · #Adversarial Robustness in Machine Learning #FOS: Electrical engineering #Multimodal Machine Learning Applications #Systems and Control (eess.SY) #Topic Modeling #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2511.00337

openalex publication_date 2025/11/01 · openalex created_date 2025/11/05 · openalex updated_date 2026/07/28

Abstract

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.

Citations

• Hybrid Modeling, Sim-to-Real Reinforcement Learning, and Large Language Model Driven Control for Digital Twins
• Large Language Models as Tool Makers
• Toolformer: Language Models Can Teach Themselves to Use Tools
• Combining physics-based and data-driven techniques for reliable hybrid analysis and modeling using the corrective source term approach

Cited by

• Evaluating LLMs as Interpretable Controllers for Dynamical Systems

Related

• Capabilities of Large Language Models in Control Engineering: A Benchmark Study on GPT-4, Claude 3 Opus, and Gemini 1.0 Ultra
• Fine-Tuning Language Models Using Formal Methods Feedback
• Plan, Eliminate, and Track -- Language Models are Good Teachers for Embodied Agents
• LLMPC: Large Language Model Predictive Control
• Large Language Models as General Pattern Machines