Automatic Adaptation Rule Optimization via Large Language Models
This addresses the problem of optimizing rule-based adaptation systems for developers, though it appears incremental as it applies existing LLM capabilities to a known bottleneck.
The paper tackles the challenge of building high-performance adaptation rules by using large language models as optimizers to construct and optimize these rules, with preliminary experiments in SWIM validating the method's effectiveness and limitations.
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.