# Large Language Models for Control

arXiv: https://arxiv.org/abs/2511.00337 · HTML: https://mlsanity.com/paper/2511.00337/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Nov 2025.

## Built on by (most cited first, 2 of 2)

- [Evaluating LLMs as Interpretable Controllers for Dynamical Systems](https://mlsanity.com/paper/2607.22609/) (2026)
- [Large Language Models in the Loop: A Stability- and Network-Aware Survey in Networked Control, Cyber-Physical, and Multi-Agent Systems](https://mlsanity.com/paper/2609.16599/) (2026)

## Abstract (arXiv)

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.