Generative Multi-Agent Collaboration in Embodied AI: A Systematic Review

TL;DR

This paper systematically reviews how generative foundation models enhance embodied multi-agent systems, improving collaboration, communication, and adaptability in complex real-world tasks across physical and virtual environments.

Contribution

It introduces a taxonomy of EMAS, analyzes key components with generative techniques, and demonstrates their transformative impact through concrete examples.

Findings

Generative models improve robustness and flexibility of EMAS.

Integration of foundation models enables richer communication among agents.

The survey highlights future challenges and promising research directions.

Abstract

Embodied multi-agent systems (EMAS) have attracted growing attention for their potential to address complex, real-world challenges in areas such as logistics and robotics. Recent advances in foundation models pave the way for generative agents capable of richer communication and adaptive problem-solving. This survey provides a systematic examination of how EMAS can benefit from these generative capabilities. We propose a taxonomy that categorizes EMAS by system architectures and embodiment modalities, emphasizing how collaboration spans both physical and virtual contexts. Central building blocks, perception, planning, communication, and feedback, are then analyzed to illustrate how generative techniques bolster system robustness and flexibility. Through concrete examples, we demonstrate the transformative effects of integrating foundation models into embodied, multi-agent frameworks. Finally, we discuss challenges and future directions, underlining the significant promise of EMAS to reshape the landscape of AI-driven collaboration.