Creativity in LLM-based Multi-Agent Systems: A Survey

TL;DR

This survey explores how creativity manifests in LLM-driven multi-agent systems, focusing on generation techniques, evaluation, and challenges to guide future research and standardization.

Contribution

It is the first comprehensive survey dedicated to creativity in multi-agent systems, providing a taxonomy, overview of techniques, datasets, metrics, and identifying key challenges.

Findings

Introduces a taxonomy of agent proactivity and personas.

Reviews generation techniques like divergent exploration and collaborative synthesis.

Identifies challenges such as evaluation inconsistency and bias mitigation.

Abstract

Large language model (LLM)-driven multi-agent systems (MAS) are transforming how humans and AIs collaboratively generate ideas and artifacts. While existing surveys provide comprehensive overviews of MAS infrastructures, they largely overlook the dimension of \emph{creativity}, including how novel outputs are generated and evaluated, how creativity informs agent personas, and how creative workflows are coordinated. This is the first survey dedicated to creativity in MAS. We focus on text and image generation tasks, and present: (1) a taxonomy of agent proactivity and persona design; (2) an overview of generation techniques, including divergent exploration, iterative refinement, and collaborative synthesis, as well as relevant datasets and evaluation metrics; and (3) a discussion of key challenges, such as inconsistent evaluation standards, insufficient bias mitigation, coordination conflicts, and the lack of unified benchmarks. This survey offers a structured framework and roadmap for advancing the development, evaluation, and standardization of creative MAS.