LLMs-guided adaptive compensator: Bringing Adaptivity to Automatic Control Systems with Large Language Models

2025-07-28

AI Summary

Adaptive control of unknown dynamical systems remains challenging due to the need for real-time parameter estimation or solving differential equations for compensator design. Method: This paper proposes an LLM-guided Model Reference Adaptive Control (MRAC) framework, where the output error between a reference model and the unknown system drives a large language model to generate structured compensation strategies—bypassing conventional parametric identification or analytic controller synthesis. Contribution/Results: Theoretically, Lyapunov stability analysis guarantees closed-loop convergence. Experimentally, the framework is validated on simulation, soft robotics, and humanoid robot platforms, reducing online computational latency by ~62% compared to traditional MRAC while improving cross-system generalization and robustness. Crucially, this work introduces the first integration of an LLM as an interpretable, verifiable adaptive compensation engine within a classical control architecture—achieving both theoretical rigor and engineering deployability.

Technology Category

• Intelligent Robots: Behavior Learning & Control
• Machine Learning: Large Multimodal Models (LMMs)
• Cognitive Modeling & Cognitive Systems: Adaptive Behavior

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

Abstract

With rapid advances in code generation, reasoning, and problem-solving, Large Language Models (LLMs) are increasingly applied in robotics. Most existing work focuses on high-level tasks such as task decomposition. A few studies have explored the use of LLMs in feedback controller design; however, these efforts are restricted to overly simplified systems, fixed-structure gain tuning, and lack real-world validation. To further investigate LLMs in automatic control, this work targets a key subfield: adaptive control. Inspired by the framework of model reference adaptive control (MRAC), we propose an LLM-guided adaptive compensator framework that avoids designing controllers from scratch. Instead, the LLMs are prompted using the discrepancies between an unknown system and a reference system to design a compensator that aligns the response of the unknown system with that of the reference, thereby achieving adaptivity. Experiments evaluate five methods: LLM-guided adaptive compensator, LLM-guided adaptive controller, indirect adaptive control, learning-based adaptive control, and MRAC, on soft and humanoid robots in both simulated and real-world environments. Results show that the LLM-guided adaptive compensator outperforms traditional adaptive controllers and significantly reduces reasoning complexity compared to the LLM-guided adaptive controller. The Lyapunov-based analysis and reasoning-path inspection demonstrate that the LLM-guided adaptive compensator enables a more structured design process by transforming mathematical derivation into a reasoning task, while exhibiting strong generalizability, adaptability, and robustness. This study opens a new direction for applying LLMs in the field of automatic control, offering greater deployability and practicality compared to vision-language models.

Problem

• Enhancing adaptive control in robotics using LLMs
• Designing compensators for system-reference alignment
• Reducing reasoning complexity in adaptive controller design

Innovation

• LLM-guided adaptive compensator framework
• Uses discrepancies for reference alignment
• Reduces reasoning complexity significantly