Toward architecting self-coding information systems

TL;DR

This paper introduces the concept of self-coding information systems, autonomous AI systems capable of self-adaptation, code generation, testing, and deployment to enhance flexibility and reduce time-to-market.

Contribution

It formally defines self-coding information systems and outlines their potential impacts and future research directions in agentic AI.

Findings

Proposes a formal definition of self-coding systems

Highlights potential for autonomous adaptation and deployment

Suggests significant impact on AI development and deployment

Abstract

In this extended abstract, we propose a novel research topic in the field of agentic AI, which we refer to as self-coding information systems. These systems will be able to dynamically adapt their structure or behavior by evaluating potential adaptation decisions, generate source code, test, and (re)deploy their source code autonomously, at runtime, reducing the time to market of new features. Here we motivate the topic, provide a formal definition of self-coding information systems, discuss some expected impacts of the new technology, and indicate potential research directions.