Agentic AI has recently emerged as a new paradigm where autonomous AI agents, empowered with Large Language Model capabilities, are capable of perceiving, reasoning and acting independently to pursue goals. In this paper, we explore the key challenges in developing Agentic AI for automated software design and modelling. These challenges include translating natural language requirements into design models, resolving ambiguities, maintaining consistency within and between design models, and managing conflicts and inconsistencies when merging different versions of a design model. To address those challenges, we propose a conceptual Multi-Agentic AI framework in which autonomous, goal-driven AI agents capable of interpreting requirements, generating design artefacts and collaborating on software design models.

Hoa Khanh Dam is Professor, Deputy Head of School (Research) & Head of Postgraduate Studies in the School of Computing and Information Technology, University of Wollongong (UOW) in Australia. He is Co-Director for the Decision System Lab at UOW. His research interests lie primarily in the intersection of Software Engineering and Artificial Intelligence (AI). He develops AI solutions for project managers, software engineers, QA and security teams to improve software quality/cybersecurity and accelerate productivity. His research also focuses on methodologies and techniques for developing AI/IoT autonomous and cyber resilient systems.