Large Language Models for Multi-Robot Systems: A Survey

2025-02-06

AI Summary

Multi-robot systems (MRS) face persistent challenges in coordination, scalability, and real-world adaptability. Method: This work systematically investigates large language model (LLM) integration paradigms for MRS, proposing a novel four-layer LLM-MRS application taxonomy—spanning task allocation, motion planning, action generation, and human–robot collaboration—validated across domestic, construction, and formation-control scenarios. It constructs the first cross-layer LLM-MRS application map, identifying critical bottlenecks including weak mathematical reasoning, hallucination, and latency. Contribution/Results: The study introduces an evolutionary pathway centered on domain-specific fine-tuning and verifiable reasoning, advocates for robust benchmark development, and unifies multi-agent coordination, robotics, and human–robot interaction theory. Supported by an actively maintained open-source GitHub repository, this work delivers a systematic, deployable guideline for operationalizing LLMs in real-world MRS applications.

Technology Category

• Intelligent Robots: Multi-Robot Systems
• Machine Learning: Large Multimodal Models (LMMs)
• Multiagent Systems: Coordination and Collaboration

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

The rapid advancement of Large Language Models (LLMs) has opened new possibilities in Multi-Robot Systems (MRS), enabling enhanced communication, task planning, and human-robot interaction. Unlike traditional single-robot and multi-agent systems, MRS poses unique challenges, including coordination, scalability, and real-world adaptability. This survey provides the first comprehensive exploration of LLM integration into MRS. It systematically categorizes their applications across high-level task allocation, mid-level motion planning, low-level action generation, and human intervention. We highlight key applications in diverse domains, such as household robotics, construction, formation control, target tracking, and robot games, showcasing the versatility and transformative potential of LLMs in MRS. Furthermore, we examine the challenges that limit adapting LLMs in MRS, including mathematical reasoning limitations, hallucination, latency issues, and the need for robust benchmarking systems. Finally, we outline opportunities for future research, emphasizing advancements in fine-tuning, reasoning techniques, and task-specific models. This survey aims to guide researchers in the intelligence and real-world deployment of MRS powered by LLMs. Based on the fast-evolving nature of research in the field, we keep updating the papers in the open-source Github repository.

Problem

• Enhancing communication in multi-robot systems
• Addressing coordination and scalability challenges
• Integrating LLMs for task and motion planning

Innovation

• LLM integration in MRS
• Task-specific model advancements
• Challenges in MRS adaptation