Towards autonomous normative multi-agent systems for Human-AI software engineering teams

TL;DR

This paper proposes autonomous AI agents with human-like reasoning, equipped with norms, to revolutionize software engineering by enabling faster, more reliable, and compliant collaboration with humans.

Contribution

It introduces a new class of normative, autonomous agents powered by Large Language Models for human-AI collaborative software development.

Findings

Agents demonstrate improved collaboration efficiency.

Normative frameworks ensure regulatory compliance.

Framework supports scalable and trustworthy Human-AI teams.

Abstract

This paper envisions a transformative paradigm in software engineering, where Artificial Intelligence, embodied in fully autonomous agents, becomes the primary driver of the core software development activities. We introduce a new class of software engineering agents, empowered by Large Language Models and equipped with beliefs, desires, intentions, and memory to enable human-like reasoning. These agents collaborate with humans and other agents to design, implement, test, and deploy software systems with a level of speed, reliability, and adaptability far beyond the current software development processes. Their coordination and collaboration are governed by norms expressed as deontic modalities - commitments, obligations, prohibitions and permissions - that regulate interactions and ensure regulatory compliance. These innovations establish a scalable, transparent and trustworthy framework for future Human-AI software engineering teams.