Autonomous Intelligent Software Development

TL;DR

This paper introduces AIDA, an autonomous developer agent that interprets requirements, reasons over a knowledge graph, and autonomously designs and generates software, improving its efficiency through learning.

Contribution

The paper presents a novel proof-of-concept for an autonomous software development agent that learns and improves by reasoning over a semantic knowledge graph.

Findings

AIDA can interpret requirements and generate software from scratch.

AIDA learns and improves its development process over time.

The knowledge graph approach enables reasoning and incremental learning.

Abstract

We present an overview of the design and first proof-of-concept implementation for AIDA, an autonomous intelligent developer agent that develops software from scratch. AIDA takes a software requirements specification and uses reasoning over a semantic knowledge graph to interpret the requirements, then designs and writes software to satisfy them. AIDA uses both declarative and procedural knowledge in the core domains of data, algorithms, and code, plus some general knowledge. The reasoning codebase uses this knowledge to identify needed components, then designs and builds the necessary information structures around them that become the software. These structures, the motivating requirements, and the resulting source code itself are all new knowledge that are added to the knowledge graph, becoming available for future reasoning. In this way, AIDA also learns as she writes code and becomes more efficient when writing subsequent code.