GAI: Generative Agents for Innovation

TL;DR

This paper introduces GAI, a framework using multiple generative agents with internal states to collaboratively innovate, demonstrated by replicating Dyson's bladeless fan invention through analogy-driven reasoning.

Contribution

The paper presents a novel GAI framework that enables collective reasoning among generative agents with internal states to facilitate innovation, a significant step beyond existing single-agent models.

Findings

Models with internal states outperform those without.

Five heterogeneous agents successfully replicated Dyson's key ideas.

Internal states enable more coherent and comprehensive idea sharing.

Abstract

This study examines whether collective reasoning among generative agents can facilitate novel and coherent thinking that leads to innovation. To achieve this, it proposes GAI, a new LLM-empowered framework designed for reflection and interaction among multiple generative agents to replicate the process of innovation. The core of the GAI framework lies in an architecture that dynamically processes the internal states of agents and a dialogue scheme specifically tailored to facilitate analogy-driven innovation. The framework's functionality is evaluated using Dyson's invention of the bladeless fan as a case study, assessing the extent to which the core ideas of the innovation can be replicated through a set of fictional technical documents. The experimental results demonstrate that models with internal states significantly outperformed those without, achieving higher average scores and lower variance. Notably, the model with five heterogeneous agents equipped with internal states successfully replicated the key ideas underlying the Dyson's invention. This indicates that the internal state enables agents to refine their ideas, resulting in the construction and sharing of more coherent and comprehensive concepts.