GAI: Generative Agents for Innovation
Masahiro Sato
TL;DR
The paper addresses replicating human-like innovation processes using AI by introducing GAI, a framework that combines memory and internal-state processing with a structured, analogy-driven dialogue scheme among multiple LLM agents. It contributes a detailed agent architecture, a Phase A–E Design by Analogy dialogue protocol, and an empirical Dyson bladeless fan case demonstrating that internal-state, heterogeneous-agent configurations markedly improve the coherence and completeness of generated innovation ideas. The findings suggest that internal states and diversified intrinsic motivations enable richer idea refinement and cross-domain transfer, enabling more faithful replication of inventive concepts within a reproducible sandbox. This work advances AI-driven innovation research by providing a scalable, controllable platform to study collective reasoning, organizational structure, and human–AI collaboration in the creative process.
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.