Automatic Adaptation Rule Optimization via Large Language Models

TL;DR

This paper explores using large language models to automatically generate and optimize adaptation rules for self-adaptive systems, aiming to improve performance and robustness.

Contribution

It introduces a novel approach employing LLMs as optimizers for adaptation rules, leveraging their reasoning capabilities.

Findings

Validated effectiveness in SWIM environment

Identified limitations of LLM-based optimization

Demonstrated potential for rapid rule development

Abstract

Rule-based adaptation is a foundational approach to self-adaptation, characterized by its human readability and rapid response. However, building high-performance and robust adaptation rules is often a challenge because it essentially involves searching the optimal design in a complex (variables) space. In response, this paper attempt to employ large language models (LLMs) as a optimizer to construct and optimize adaptation rules, leveraging the common sense and reasoning capabilities inherent in LLMs. Preliminary experiments conducted in SWIM have validated the effectiveness and limitation of our method.