Generative Multi-Agent Collaboration in Embodied AI: A Systematic Review
It addresses the problem of advancing AI-driven collaboration in embodied settings for researchers and practitioners, but it is incremental as a review paper.
This survey examines how generative capabilities from foundation models can enhance embodied multi-agent systems (EMAS) for complex real-world challenges like logistics and robotics, proposing a taxonomy and analyzing key components to demonstrate improved robustness and flexibility.
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.