The Vision of Autonomic Computing: Can LLMs Make It a Reality?
Zhiyang Zhang, Fangkai Yang, Xiaoting Qin, Jue Zhang, Qingwei Lin, Gong Cheng, Dongmei Zhang, Saravan Rajmohan, Qi Zhang
2024-07-22
Summary
This paper discusses the concept of Autonomic Computing and explores how Large Language Models (LLMs) can help make it a reality. Autonomic Computing refers to systems that can manage themselves automatically, similar to how living organisms adapt to their environments.
What's the problem?
Despite the idea of Autonomic Computing being around for over 20 years, achieving it has been difficult. Modern computing systems are very complex and constantly changing, making it hard for them to self-manage effectively. This complexity means that traditional methods often fall short in creating systems that can adapt and respond to new situations without human intervention.
What's the solution?
The authors propose using an LLM-based framework to manage microservices, which are small, independent services that work together in larger applications. They introduce a five-level system to classify how autonomous these services can be and present a benchmark based on the Sock Shop microservice demo project to evaluate their framework's performance. Their findings show that LLMs can significantly improve the ability of these systems to detect and fix problems on their own, achieving a notable level of autonomy.
Why it matters?
This research is important because it pushes the boundaries of what AI can do in managing computing systems. By integrating LLMs into microservice management, we move closer to creating systems that can operate independently, reducing the need for constant human oversight. This could lead to more efficient and reliable computing environments in various industries, ultimately enhancing productivity and innovation.
Abstract
The Vision of Autonomic Computing (ACV), proposed over two decades ago, envisions computing systems that self-manage akin to biological organisms, adapting seamlessly to changing environments. Despite decades of research, achieving ACV remains challenging due to the dynamic and complex nature of modern computing systems. Recent advancements in Large Language Models (LLMs) offer promising solutions to these challenges by leveraging their extensive knowledge, language understanding, and task automation capabilities. This paper explores the feasibility of realizing ACV through an LLM-based multi-agent framework for microservice management. We introduce a five-level taxonomy for autonomous service maintenance and present an online evaluation benchmark based on the Sock Shop microservice demo project to assess our framework's performance. Our findings demonstrate significant progress towards achieving Level 3 autonomy, highlighting the effectiveness of LLMs in detecting and resolving issues within microservice architectures. This study contributes to advancing autonomic computing by pioneering the integration of LLMs into microservice management frameworks, paving the way for more adaptive and self-managing computing systems. The code will be made available at https://aka.ms/ACV-LLM.