This repo is constructed for collecting and categorizing papers about the application of LLMs in multi-robot systmes (MRS) to our survey paper: Large Language Models for Multi-Robot Systems: A Survey. We will keep updating new papers in this field here in the repository.
Please cite our survey paper if you find our work useful:
@article{li2025large,
title={Large Language Models for Multi-Robot Systems: A Survey},
author={Li, Peihan and An, Zijian and Abrar, Shams and Zhou, Lifeng},
journal={arXiv preprint arXiv:2502.03814},
year={2025}
}
We categorize the applications of LLMs in MRS into high-level task allocation, mid-level motion planning, low-level action generation, and human intervention scenarios. High-level task planning involves tasks that demand a higher degree of intelligence, such as task allocation and planning among multiple robots, where the LLM is required to exhibit logical reasoning and decision-making capabilities. Mid-level motion planning refers to navigation or path-planning scenarios. Low-level action generation uses LLMs to generate and directly control robots' posture or motion. On the other hand, human intervention involves using LLMs to interact with human operators and guide task planning and execution.
[2024/12] Design of a Multi-Robot Coordination System based on Functional Expressions using Large Language Models. Yuki Kato et al. [paper]
[2024/11] DART-LLM: Dependency-Aware Multi-Robot Task Decomposition and Execution using Large Language Models. Yongdong Wang et al. [paper]
[2024/10] EMOS: Embodiment-aware Heterogeneous Multi-robot Operating System with LLM Agents. Junting Chen et al. [paper]
[2024/10] LiP-LLM: Integrating Linear Programming and Dependency Graph with Large Language Models for Multi-Robot Task Planning. Kazuma Obata et al. [paper]
[2024/10] Verification of a Two-Step Inference Model for Cooperative Evaluation of Robot Actions Using Foundation Models. Takahiro Yoshida et al.
[2024/09] REBEL: Rule-based and Experience-enhanced Learning with LLMs for Initial Task Allocation in Multi-Human Multi-Robot Teams. Arjun Gupte et al. [paper]
[2024/09] COHERENT: Collaboration of Heterogeneous Multi-Robot System with Large Language Models. Kehui Liu et al. [paper]
[2024/09] MHRC: Closed-loop Decentralized Multi-Heterogeneous Robot Collaboration with Large Language Models. Wenhao Yu et al. [paper]
[2024/09] Hierarchical LLMs In-the-loop Optimization for Real-time Multi-Robot Target Tracking under Unknown Hazards. Yuwei Wu et al. [paper]
[2024/08] Scaling Up Natural Language Understanding for Multi-Robots Through the Lens of Hierarchy. Shaojun Xu et al. [paper]
[2024/06] LLCoach: Generating Robot Soccer Plans using Multi-Role Large Language Models. Michele Brienza et al. [paper]
[2024/05] VADER: Visual Affordance Detection and Error Recovery for Multi-Robot Human Collaboration. Michael Ahn et al. [paper]
[2024/03] Can Large Language Models Solve Robot Routing?. Zhehui Huang et al. [paper]
[2024/02] Conversational Language Models for Human-in-the-Loop Multi-Robot Coordination. William Hunt et al. [paper]
[2024/02] Probabilistically Correct Language-Based Multi-Robot Planning Using Conformal Prediction. Jun Wang et al. [paper]
[2024] LLM Assistant for Heterogeneous Multi-Robot System Dynamic Task Planning. Miguel Guzmán-Merino et al. [paper]
[2023/12] LLM-MARS: Large Language Model for Behavior Tree Generation and NLP-Enhanced Dialogue in Multi-Agent Robot Systems. Artem Lykov et al. [paper]
[2023/12] Exploring Large Language Models to Facilitate Variable Autonomy for Human-Robot Teaming. Younes Lakhnati et al. [paper]
[2023/09] Scalable Multi-Robot Collaboration with Large Language Models: Centralized or Decentralized Systems?. Yongchao Chen et al. [paper]
[2023/09] Smart-LLM: Smart Multi-Agent Robot Task Planning using Large Language Models. Shyam Sundar Kannan et al. [paper]
[2023/07] RoCo: Dialectic Multi-Robot Collaboration with Large Language Models. Zhao Mandi et al. [paper]
[2024/10] MARLIN: Multi-Agent Reinforcement Learning Guided by Language-Based Inter-Robot Negotiation. Toby Godfrey et al. [paper]
[2024/09] Hierarchical LLMs In-the-loop Optimization for Real-time Multi-Robot Target Tracking under Unknown Hazards. Yuwei Wu et al. [paper]
[2024/07] Language-Conditioned Offline RL for Multi-Robot Navigation. Steven Morad et al. [paper]
[2024/07] CAMoN: Cooperative Agents for Multi-Object Navigation with LLM-Based Conversations. Pengying Wu et al. [paper]
[2024/04] Foundation Models to the Rescue: Deadlock Resolution in Connected Multi-Robot Systems. Kunal Garg et al. [paper]
[2023/10] Co-NavGPT: Multi-Robot Cooperative Visual Semantic Navigation using Large Language Models. Bangguo Yu et al. [paper]
[2024/10] LLM2Swarm: Robot Swarms that Responsively Reason, Plan, and Collaborate through LLMs. Volker Strobel et al. [paper]
[2024/05] FlockGPT: Guiding UAV Flocking with Linguistic Orchestration. Artem Lykov et al. [paper]
[2024/04] Challenges Faced by Large Language Models in Solving Multi-Agent Flocking. Peihan Li et al. [paper]
[2024/04] ZeroCAP: Zero-Shot Multi-Robot Context Aware Pattern Formation via Large Language Models. Vishnunandan LN Venkatesh et al. [paper]
[2024/01] Why Solving Multi-Agent Path Finding with Large Language Model Has Not Succeeded Yet. Weizhe Chen et al. [paper]
Please contact Peihan Li ([email protected]) and Lifeng Zhou ([email protected]) with any questions or comments.