Multi-agent Embodied AI: Advances and Future Directions

TL;DR

The paper surveys the rise of embodied AI and its expansion from single-agent systems to multi-agent embodied AI (MAS), emphasizing the unique challenges of open, dynamic environments and heterogeneous agent teams. It systematically reviews foundations (OC, RL, HL, IL, Generative Models), single-agent methods (classic planning, end-to-end RL, and generative-model-based approaches), and the burgeoning field of multi-agent embodied AI (control, learning, and generative-model coordination) along with benchmarks. Key contributions include a structured synthesis of methods, benchmarks, and open challenges, plus a forward-looking roadmap covering theory, scalable algorithms, data-efficient learning, and large generative-model integration. The work aims to guide researchers and practitioners toward robust, scalable, and safe multi-agent embodied AI systems with real-world impact.

Abstract

Embodied artificial intelligence (Embodied AI) plays a pivotal role in the application of advanced technologies in the intelligent era, where AI systems are integrated with physical bodies that enable them to perceive, reason, and interact with their environments. Through the use of sensors for input and actuators for action, these systems can learn and adapt based on real-world feedback, allowing them to perform tasks effectively in dynamic and unpredictable environments. As techniques such as deep learning (DL), reinforcement learning (RL), and large language models (LLMs) mature, embodied AI has become a leading field in both academia and industry, with applications spanning robotics, healthcare, transportation, and manufacturing. However, most research has focused on single-agent systems that often assume static, closed environments, whereas real-world embodied AI must navigate far more complex scenarios. In such settings, agents must not only interact with their surroundings but also collaborate with other agents, necessitating sophisticated mechanisms for adaptation, real-time learning, and collaborative problem-solving. Despite increasing interest in multi-agent systems, existing research remains narrow in scope, often relying on simplified models that fail to capture the full complexity of dynamic, open environments for multi-agent embodied AI. Moreover, no comprehensive survey has systematically reviewed the advancements in this area. As embodied AI rapidly evolves, it is crucial to deepen our understanding of multi-agent embodied AI to address the challenges presented by real-world applications. To fill this gap and foster further development in the field, this paper reviews the current state of research, analyzes key contributions, and identifies challenges and future directions, providing insights to guide innovation and progress in this field.

Figures (23)

• Figure 1: An overview of this survey.
• Figure 2: An illustration of embodied AI.
• Figure 3: Three common settings of MAS.
• Figure 4: An illustration of MPC.
• Figure 5: An illustration of RL and MARL.