Augmenting Divergent and Convergent Thinking in the Ideation Process : An LLM-Based Agent System

Titelangaben

Fischer-Brandies, Leopold ; Meierhöfer, Simon ; Protschky, Dominik:
Augmenting Divergent and Convergent Thinking in the Ideation Process : An LLM-Based Agent System.
In: Proceedings of the 32nd European Conference on Information Systems (ECIS). - Paphos, Cyprus , 2024
ISBN 978-1-958200-10-0

Volltext

Link zum Volltext (externe URL):

Abstract

Generative Artificial Intelligence (GenAI) in general and Large Language Models (LLMs) in particular
have recently gained considerable attention in innovation management as a means to augment the
generation of innovative ideas. While this trend seems to grow at an astonishing pace, knowledge on
how to leverage the transformative potential of LLMs for idea generation is scarce in the scientific
literature. This poses a major challenge for organizations seeking to channel the inherent capabilities
of LLMs for the generation of innovative ideas in a meaningful and efficacious manner. Against this
backdrop, we design and instantiate an artifact that augments divergent and convergent thinking in the
ideation process with the help of LLMs (i.e., an LLM-based agent system for ideation), following the
design science research paradigm. Based on the insights from ten interviews with subject matter experts,
we conclude that the use of the artifact in the ideation processes is applicable and useful.