pith. sign in

arxiv: 2502.03814 · v5 · submitted 2025-02-06 · 💻 cs.RO · cs.AI

Large Language Models for Multi-Robot Systems: A Survey

Peihan Li , Zijian An , Shams Abrar , Lifeng Zhou This is my paper

Pith reviewed 2026-05-23 04:29 UTC · model grok-4.3

classification 💻 cs.RO cs.AI
keywords Large Language ModelsMulti-Robot SystemsTask AllocationMotion PlanningAction GenerationHuman-Robot InteractionSurveyChallenges
0
0 comments X

The pith

This survey is the first to systematically review LLM integration into multi-robot systems and organize the applications into four abstraction levels.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper establishes that large language models can be applied to multi-robot systems for improved coordination, planning, and interaction in ways that go beyond single-robot or traditional multi-agent setups. It organizes existing work into high-level task allocation, mid-level motion planning, low-level action generation, and human intervention, while reviewing domains such as household robotics and construction. A sympathetic reader would care because the categorization makes the scattered literature usable for guiding new research and deployment. The survey also flags practical barriers including hallucination, latency, and weak mathematical reasoning, then lists directions such as better fine-tuning and task-specific models.

Core claim

This survey provides the first dedicated review 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, highlights applications in domains such as household robotics, construction, formation control, target tracking, and robot games, examines challenges including mathematical reasoning limitations, hallucination, latency issues, and the need for robust benchmarking, and outlines opportunities in fine-tuning, reasoning techniques, and task-specific models.

What carries the argument

The four-level categorization framework that partitions LLM uses in MRS by abstraction level from task allocation down to action generation and human intervention.

If this is right

  • The categorization allows researchers to map existing work and spot gaps in LLM support for MRS coordination.
  • Addressing hallucination and latency becomes a prerequisite for reliable low-level action generation in real robots.
  • Task-specific fine-tuning and improved reasoning methods would directly expand the usable range of high-level task allocation.
  • Robust benchmarking systems would enable quantitative comparison across the four levels.
  • Continuous updates via the linked repository keep the mapping current as new papers appear.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The same four-level lens could be tested on LLM uses in non-robotic multi-agent systems such as software agents or sensor networks.
  • Hybrid architectures that combine LLMs with classical control loops at the lowest level might reduce latency without losing high-level reasoning.
  • Domain-specific datasets drawn from the reviewed applications could accelerate the creation of the task-specific models the survey recommends.
  • Scalability limits mentioned for MRS would become measurable once the benchmarking systems the paper calls for are built.

Load-bearing premise

The reviewed literature is sufficiently complete and the four levels cleanly partition applications without major overlap or missing categories.

What would settle it

A set of published LLM-MRS papers whose applications cannot be assigned to any of the four levels or that exhibit substantial overlap between levels.

read the original abstract

The rapid advancement of Large Language Models (LLMs) has opened new possibilities in Multi-Robot Systems (MRS), enabling enhanced communication, task allocation and 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 dedicated review 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 to 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. Given the rapidly evolving nature of research in the field, we continuously update the paper list in the open-source GitHub repository.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

1 major / 2 minor

Summary. The manuscript is a survey claiming to be the first dedicated review of Large Language Model (LLM) integration into Multi-Robot Systems (MRS). It categorizes applications into four levels—high-level task allocation, mid-level motion planning, low-level action generation, and human intervention—while discussing domain examples (household robotics, construction, formation control, target tracking, robot games), challenges (mathematical reasoning limits, hallucination, latency, benchmarking), and future opportunities (fine-tuning, reasoning techniques, task-specific models). The work notes that the paper list is maintained via an open GitHub repository due to the field's rapid evolution.

Significance. If the taxonomy is shown to be comprehensive and the coverage complete, the survey would provide a useful organizing framework for researchers working at the intersection of LLMs and MRS, highlighting both application domains and practical deployment barriers. The explicit commitment to an open, continuously updated GitHub repository is a strength for a fast-moving area and supports reproducibility of the literature list.

major comments (1)
  1. [Abstract and Introduction] Abstract and Introduction: the claim of providing a 'systematic' categorization and the 'first dedicated review' is load-bearing for the paper's positioning, yet the manuscript does not describe the search protocol, databases queried, keywords, date range, or inclusion/exclusion criteria. Without this information it is not possible to evaluate whether the four-level taxonomy is supported by exhaustive coverage or whether important papers fall outside the stated categories.
minor comments (2)
  1. The GitHub repository URL should be stated explicitly in the abstract or a prominent footnote so readers can immediately access the updated paper list.
  2. Figure captions and table headings would benefit from clearer indication of which cited works fall into each of the four taxonomy levels to help readers trace the categorization.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for highlighting this important methodological gap. We agree that the claims of a 'systematic' categorization and 'first dedicated review' require explicit documentation of the literature search process to allow proper evaluation of coverage and taxonomy validity. We will revise the manuscript to address this.

read point-by-point responses

  1. Referee: [Abstract and Introduction] Abstract and Introduction: the claim of providing a 'systematic' categorization and the 'first dedicated review' is load-bearing for the paper's positioning, yet the manuscript does not describe the search protocol, databases queried, keywords, date range, or inclusion/exclusion criteria. Without this information it is not possible to evaluate whether the four-level taxonomy is supported by exhaustive coverage or whether important papers fall outside the stated categories.

    Authors: We acknowledge that the manuscript currently lacks a description of the search protocol, which is a valid concern for substantiating the systematic nature of the survey. In the revised version, we will insert a new subsection 'Literature Search and Taxonomy Development' immediately after the Introduction's motivation paragraph. This subsection will specify: (1) databases queried (arXiv, Google Scholar, IEEE Xplore, ACM Digital Library); (2) search strings and keywords (combinations of 'large language model' OR LLM with 'multi-robot system' OR 'multi-agent robot' OR MRS, plus domain terms like task allocation, motion planning); (3) date range (primarily 2022–2024, reflecting the post-GPT-3 emergence of relevant work, with earlier foundational papers included where directly relevant); (4) inclusion criteria (papers that explicitly integrate LLMs with multi-robot coordination, planning, or interaction, including both peer-reviewed and high-quality arXiv preprints); and (5) exclusion criteria (single-robot LLM applications, purely simulation-based multi-agent work without physical MRS considerations, or papers using LLMs only for unrelated tasks). We will also note that the open GitHub repository serves as the living record for ongoing additions. This addition will enable readers to assess whether the four-level taxonomy (task allocation, motion planning, action generation, human intervention) comprehensively captures the literature. revision: yes

Circularity Check

0 steps flagged

No significant circularity

full rationale

This is a literature survey paper with no mathematical derivations, equations, fitted parameters, predictions, or uniqueness theorems. The central claims (first dedicated review; four-level taxonomy) are organizational statements about existing literature rather than results derived from internal inputs. No self-citation chains or ansatzes are load-bearing for any technical result. The paper is self-contained as a review and receives the default non-circularity outcome.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

As a survey paper, the work introduces no free parameters, axioms, or invented entities; it relies entirely on previously published research in robotics and AI.

pith-pipeline@v0.9.0 · 5745 in / 1122 out tokens · 33131 ms · 2026-05-23T04:29:35.946586+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. LLM-Foraging: Large Language Models for Decentralized Swarm Robot Foraging

    cs.RO 2026-05 unverdicted novelty 7.0

    LLM-Foraging uses off-the-shelf LLMs for decentralized tactical decisions in CPFA-based swarm foraging, collecting more resources than GA-tuned baselines across 36 varied configurations while showing greater consistency.

  2. Semantic Risk-Aware Heuristic Planning for Robotic Navigation in Dynamic Environments: An LLM-Inspired Approach

    cs.RO 2026-05 unverdicted novelty 5.0

    SRAH planner using LLM-inspired semantic costs in A* search raises simulated robot task success from 56.5% (BFS) to 62% across 200 grid-world trials with dynamic obstacles.

  3. Event-Triggered Adaptive Consensus for Multi-Robot Task Allocation

    cs.MA 2026-04 unverdicted novelty 5.0

    An event-triggered consensus framework for heterogeneous robot swarms reduces communication overhead while preserving high task completion rates and resilience to failures in simulations.

  4. Adaptive Obstacle-Aware Task Assignment and Planning for Heterogeneous Robot Teaming

    cs.RO 2025-10 unverdicted novelty 5.0

    OATH combines adaptive Halton sampling, obstacle-aware clustering with auctions, and LLM-based instruction interpretation to improve task assignment and planning for heterogeneous robot teams in obstacle-rich environments.

  5. Vision-and-Language Navigation for UAVs: Progress, Challenges, and a Research Roadmap

    cs.RO 2026-04 unverdicted novelty 4.0

    A survey of UAV vision-and-language navigation that establishes a methodological taxonomy, reviews resources and challenges, and proposes a forward-looking research roadmap.

  6. When control meets large language models: From words to dynamics

    eess.SY 2026-02 unverdicted novelty 3.0

    The paper proposes a bidirectional continuum between LLMs and control systems, covering LLM-assisted controller design, control-based LLM steering, and state-space modeling of LLMs.

Reference graph

Works this paper leans on

152 extracted references · 152 canonical work pages · cited by 6 Pith papers · 26 internal anchors

  1. [1]

    GPT-4 Technical Report

    Josh Achiam, Steven Adler, Sandhini Agar- wal, Lama Ahmad, Ilge Akkaya, Floren- cia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anad- kat, et al. Gpt-4 technical report. arXiv preprint arXiv:2303.08774, 2023

    work page internal anchor Pith review Pith/arXiv arXiv 2023

  2. [2]

    Joshi, Daniel Lam, Tsang- Wei Edward Lee, Alex Luong, Sharath Maddineni, Harsh Patel, Jodilyn Peralta, Jornell Quiambao, Diego Reyes, Rosario M

    Michael Ahn, Montserrat Gonzalez Are- nas, Matthew Bennice, Noah Brown, Chris- tine Chan, Byron David, Anthony Francis, Gavin Gonzalez, Rainer Hessmer, Tomas Jackson, Nikhil J. Joshi, Daniel Lam, Tsang- Wei Edward Lee, Alex Luong, Sharath Maddineni, Harsh Patel, Jodilyn Peralta, Jornell Quiambao, Diego Reyes, Rosario M. Jauregui Ruano, Dorsa Sadigh, Pan- ...

    work page arXiv 2024

  3. [3]

    The Falcon Series of Open Language Models

    Ebtesam Almazrouei, Hamza Alobeidli, Abdulaziz Alshamsi, Alessandro Cappelli, Ruxandra Cojocaru, M´ erouane Debbah, ´Etienne Goffinet, Daniel Hesslow, Julien Launay, Quentin Malartic, et al. The fal- con series of open language models. arXiv preprint arXiv:2311.16867, 2023

    work page internal anchor Pith review Pith/arXiv arXiv 2023

  4. [4]

    Local motion planning for collaborative multi- robot manipulation of deformable objects

    Javier Alonso-Mora, Ross Knepper, Roland Siegwart, and Daniela Rus. Local motion planning for collaborative multi- robot manipulation of deformable objects. In 2015 IEEE international conference on robotics and automation (ICRA), pages 5495–5502. IEEE, 2015. 23

    work page 2015

  5. [5]

    Dis- tributed multi-robot formation control among obstacles: A geometric and optimiza- tion approach with consensus

    Javier Alonso-Mora, Eduardo Montijano, Mac Schwager, and Daniela Rus. Dis- tributed multi-robot formation control among obstacles: A geometric and optimiza- tion approach with consensus. In 2016 IEEE international conference on robotics and automation (ICRA), pages 5356–5363. IEEE, 2016

    work page 2016

  6. [6]

    Multi-robot systems and cooperative object transport: Communications, platforms, and challenges

    Xing An, Celimuge Wu, Yangfei Lin, Min Lin, Tsutomu Yoshinaga, and Yusheng Ji. Multi-robot systems and cooperative object transport: Communications, platforms, and challenges. IEEE Open Journal of the Computer Society, 4:23–36, 2023

    work page 2023

  7. [7]

    Claude, 2024

    Anthropic. Claude, 2024. Accessed via Anthropic API

    work page 2024

  8. [8]

    Multi-robot search and rescue: A potential field based approach

    Joseph L Baxter, EK Burke, Jonathan M Garibaldi, and Mark Norman. Multi-robot search and rescue: A potential field based approach. Autonomous robots and agents, pages 9–16, 2007

    work page 2007

  9. [9]

    Small Language Models are the Future of Agentic AI

    Peter Belcak, Greg Heinrich, Shizhe Diao, Yonggan Fu, Xin Dong, Saurav Muralid- haran, Yingyan Celine Lin, and Pavlo Molchanov. Small language models are the future of agentic ai. arXiv preprint arXiv:2506.02153, 2025

    work page internal anchor Pith review Pith/arXiv arXiv 2025

  10. [10]

    LLCoach: Generating Robot Soc- cer Plans using Multi-Role Large Language Models

    Michele Brienza, Emanuele Musumeci, Vin- cenzo Suriani, Daniele Affinita, Andrea Pen- nisi, Daniele Nardi, and Domenico Daniele Bloisi. LLCoach: Generating Robot Soc- cer Plans using Multi-Role Large Language Models. arXiv preprint arXiv:2406.18285, June 2024

    work page arXiv 2024

  11. [11]

    RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control

    Anthony Brohan, Noah Brown, Justice Carbajal, Yevgen Chebotar, Xi Chen, Krzysztof Choromanski, Tianli Ding, D Driess, A Dubey, C Finn, et al. Rt-2: Vision-language-action models transfer web knowledge to robotic control. arxiv. arXiv preprint arXiv:2307.15818, 2023

    work page internal anchor Pith review Pith/arXiv arXiv 2023

  12. [12]

    Coor- dinated multi-robot exploration

    Wolfram Burgard, Mark Moors, Cyrill Stachniss, and Frank E Schneider. Coor- dinated multi-robot exploration. IEEE Transactions on robotics, 21(3):376–386, 2005

    work page 2005

  13. [13]

    Energy- aware routing algorithm for mobile ground- to-air charging

    Bill Cai, Fei Lu, and Lifeng Zhou. Energy- aware routing algorithm for mobile ground- to-air charging. In 2024 IEEE International Symposium of Robotics Research (ISRR). IEEE, 2024

    work page 2024

  14. [14]

    Multi- agent systems for robotic autonomy with llms

    Junhong Chen, Ziqi Yang, Haoyuan G Xu, Dandan Zhang, and George Mylonas. Multi- agent systems for robotic autonomy with llms. In Proceedings of the Computer Vision and Pattern Recognition Conference, pages 4194–4204, 2025

    work page 2025

  15. [15]

    EMOS: Embodiment-aware Het- erogeneous Multi-robot Operating Sys- tem with LLM Agents

    Junting Chen, Checheng Yu, Xunzhe Zhou, Tianqi Xu, Yao Mu, Mengkang Hu, Wenqi Shao, Yikai Wang, Guohao Li, and Lin Shao. EMOS: Embodiment-aware Het- erogeneous Multi-robot Operating Sys- tem with LLM Agents. arXiv preprint arXiv:2410.22662, October 2024

    work page arXiv 2024

  16. [16]

    Learning decen- tralized flocking controllers with spatio- temporal graph neural network

    Siji Chen, Yanshen Sun, Peihan Li, Lifeng Zhou, and Chang-Tien Lu. Learning decen- tralized flocking controllers with spatio- temporal graph neural network. In 2024 IEEE International Conference on Robotics and Automation (ICRA), pages 2596–2602. IEEE, 2024

    work page 2024

  17. [17]

    Why Solving Multi-agent Path Finding with Large Language Model has not Succeeded Yet

    Weizhe Chen, Sven Koenig, and Bis- tra Dilkina. Why Solving Multi-agent Path Finding with Large Language Model has not Succeeded Yet. arXiv preprint arXiv:2401.03630, feb 2024

    work page arXiv 2024

  18. [18]

    Yongchao Chen, Jacob Arkin, Yang Zhang, Nicholas Roy, and Chuchu Fan. Scal- able Multi-Robot Collaboration with Large Language Models: Centralized or Decentral- ized Systems? In 2024 IEEE International Conference on Robotics and Automation (ICRA), pages 4311–4317, May 2024

    work page 2024

  19. [19]

    Air- ground collaboration for language-specified missions in unknown environments

    Fernando Cladera, Zachary Ravichandran, Jason Hughes, Varun Murali, Carlos Nieto- Granda, M Ani Hsieh, George J Pappas, Camillo J Taylor, and Vijay Kumar. Air- ground collaboration for language-specified missions in unknown environments. arXiv preprint arXiv:2505.09108, 2025. 24

    work page arXiv 2025

  20. [20]

    Coor- dinated control of multi-robot systems: A survey

    Jorge Cort´ es and Magnus Egerstedt. Coor- dinated control of multi-robot systems: A survey. SICE Journal of Control, Measurement, and System Integration, 10(6):495–503, 2017

    work page 2017

  21. [21]

    Pybullet, a python module for physics simulation for games, robotics and machine learning

    Erwin Coumans and Yunfei Bai. Pybullet, a python module for physics simulation for games, robotics and machine learning. http: //pybullet.org, 2016–2021

    work page 2016

  22. [22]

    Parameter-efficient fine-tuning of large-scale pre-trained language models

    Ning Ding, Yujia Qin, Guang Yang, Fuchao Wei, Zonghan Yang, Yusheng Su, Shengding Hu, Yulin Chen, Chi-Min Chan, Weize Chen, et al. Parameter-efficient fine-tuning of large-scale pre-trained language models. Nature Machine Intelligence, 5(3):220–235, 2023

    work page 2023

  23. [23]

    The Llama 3 Herd of Models

    Abhimanyu Dubey, Abhinav Jauhri, Abhi- nav Pandey, Abhishek Kadian, Ahmad Al- Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Amy Yang, Angela Fan, et al. The llama 3 herd of models. arXiv preprint arXiv:2407.21783, 2024

    work page internal anchor Pith review Pith/arXiv arXiv 2024

  24. [24]

    Multi-robot teams for environ- mental monitoring

    Maria Valera Espina, Raphael Grech, Deon De Jager, Paolo Remagnino, Luca Iocchi, Luca Marchetti, Daniele Nardi, Dorothy Monekosso, Mircea Nicolescu, and Christo- pher King. Multi-robot teams for environ- mental monitoring. Innovations in Defence Support Systems–3: Intelligent Paradigms in Security, pages 183–209, 2011

    work page 2011

  25. [25]

    Foundation models in robotics: Applications, challenges, and the future,

    Roya Firoozi, Johnathan Tucker, Stephen Tian, Anirudha Majumdar, Jiankai Sun, Weiyu Liu, Yuke Zhu, Shuran Song, Ashish Kapoor, Karol Hausman, Brian Ichter, Danny Driess, Jiajun Wu, Cewu Lu, and Mac Schwager. Foundation Models in Robotics: Applications, Challenges, and the Future. arXiv preprint arXiv:2312.07843, December 2023

    work page arXiv 2023

  26. [26]

    Violet: End-to-end video-language transformers with masked visual-token modeling

    Tsu-Jui Fu, Linjie Li, Zhe Gan, Kevin Lin, William Yang Wang, Lijuan Wang, and Zicheng Liu. Violet: End-to-end video-language transformers with masked visual-token modeling. arXiv preprint arXiv:2111.12681, 2021

    work page arXiv 2021

  27. [27]

    Meeting-merging-mission: A multi-robot coordinate framework for large-scale communication-limited explo- ration

    Yuman Gao, Yingjian Wang, Xingguang Zhong, Tiankai Yang, Mingyang Wang, Zhixiong Xu, Yongchao Wang, Yi Lin, Chao Xu, and Fei Gao. Meeting-merging-mission: A multi-robot coordinate framework for large-scale communication-limited explo- ration. In 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pages 13700–13707. IEEE, 2022

    work page 2022

  28. [28]

    Retrieval-Augmented Generation for Large Language Models: A Survey

    Yunfan Gao, Yun Xiong, Xinyu Gao, Kangxiang Jia, Jinliu Pan, Yuxi Bi, Yi Dai, Jiawei Sun, and Haofen Wang. Retrieval-augmented generation for large language models: A survey. arXiv preprint arXiv:2312.10997, 2023

    work page internal anchor Pith review Pith/arXiv arXiv 2023

  29. [29]

    Foundation Models to the Rescue: Deadlock Resolution in Connected Multi-Robot Systems

    Kunal Garg, Songyuan Zhang, Jacob Arkin, and Chuchu Fan. Foundation Models to the Rescue: Deadlock Resolution in Connected Multi-Robot Systems. arXiv preprint arXiv:2404.06413, September 2024

    work page arXiv 2024

  30. [30]

    A critical review of communications in multi-robot systems

    Jennifer Gielis, Ajay Shankar, and Amanda Prorok. A critical review of communications in multi-robot systems. Current robotics reports, 3(4):213–225, 2022

    work page 2022

  31. [31]

    Toby Godfrey, William Hunt, and Moham- mad D. Soorati. MARLIN: Multi- Agent Reinforcement Learning Guided by Language-Based Inter-Robot Negotiation. arXiv preprint arXiv:2410.14383, October 2024

    work page internal anchor Pith review Pith/arXiv arXiv 2024

  32. [32]

    Gemini, 2024

    Google. Gemini, 2024. Accessed [Date accessed], Google AI system

    work page 2024

  33. [33]

    Cooperative air and ground surveillance

    Ben Grocholsky, James Keller, Vijay Kumar, and George Pappas. Cooperative air and ground surveillance. IEEE Robotics & Automation Magazine, 13(3):16–25, 2006

    work page 2006

  34. [34]

    DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

    Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, Qihao Zhu, Shirong Ma, Peiyi Wang, Xiao Bi, et al. Deepseek-r1: Incentivizing rea- soning capability in llms via reinforcement learning. arXiv preprint arXiv:2501.12948, 2025. 25

    work page internal anchor Pith review Pith/arXiv arXiv 2025

  35. [35]

    Large Language Model based Multi-Agents: A Survey of Progress and Challenges

    Taicheng Guo, Xiuying Chen, Yaqi Wang, Ruidi Chang, Shichao Pei, Nitesh V. Chawla, Olaf Wiest, and Xiangliang Zhang. Large Language Model based Multi-Agents: A Survey of Progress and Challenges. arXiv preprint arXiv:2402.01680, April 2024

    work page internal anchor Pith review Pith/arXiv arXiv 2024

  36. [36]

    Generalized mis- sion planning for heterogeneous multi-robot teams via llm-constructed hierarchical trees

    Piyush Gupta, David Isele, Enna Sachdeva, Pin-Hao Huang, Behzad Dariush, Kwonjoon Lee, and Sangjae Bae. Generalized mis- sion planning for heterogeneous multi-robot teams via llm-constructed hierarchical trees. arXiv preprint arXiv:2501.16539, 2025

    work page arXiv 2025

  37. [37]

    Arjun Gupte, Ruiqi Wang, Vishnunandan L. N. Venkatesh, Taehyeon Kim, Dezhong Zhao, and Byung-Cheol Min. REBEL: Rule- based and Experience-enhanced Learning with LLMs for Initial Task Allocation in Multi-Human Multi-Robot Teams. arXiv preprint arXiv:2409.16266, September 2024

    work page arXiv 2024

  38. [38]

    LLM Assistant for heterogeneous multi-robot system dynamic task planning

    Miguel Guzm´ an-Merino and Nils S¨ oren Krause. LLM Assistant for heterogeneous multi-robot system dynamic task planning. September 2024. Publisher: Technische Uni- versit¨ at Hamburg, Institut f¨ ur Digitales und Autonomes Bauen

    work page 2024

  39. [39]

    LoRA: Low-Rank Adaptation of Large Language Models

    Edward J Hu, Yelong Shen, Phillip Wal- lis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. Lora: Low-rank adaptation of large language mod- els. arXiv preprint arXiv:2106.09685, 2021

    work page internal anchor Pith review Pith/arXiv arXiv 2021

  40. [40]

    A survey on halluci- nation in large language models: Principles, taxonomy, challenges, and open questions

    Lei Huang, Weijiang Yu, Weitao Ma, Wei- hong Zhong, Zhangyin Feng, Haotian Wang, Qianglong Chen, Weihua Peng, Xiaocheng Feng, Bing Qin, et al. A survey on halluci- nation in large language models: Principles, taxonomy, challenges, and open questions. ACM Transactions on Information Systems, 2023

    work page 2023

  41. [41]

    From words to routes: Apply- ing large language models to vehicle routing

    Zhehui Huang, Guangyao Shi, and Gaurav S Sukhatme. From words to routes: Apply- ing large language models to vehicle routing. arXiv preprint arXiv:2403.10795, 2024

    work page arXiv 2024

  42. [42]

    Compositional coordination for multi-robot teams with large language models

    Zhehui Huang, Guangyao Shi, Yuwei Wu, Vijay Kumar, and Gaurav S Sukhatme. Compositional coordination for multi-robot teams with large language models. arXiv preprint arXiv:2507.16068, 2025

    work page arXiv 2025

  43. [43]

    Conversational language models for human-in-the-loop multi- robot coordination

    William Hunt, Toby Godfrey, and Moham- mad D Soorati. Conversational language models for human-in-the-loop multi- robot coordination. arXiv preprint arXiv:2402.19166, 2024

    work page arXiv 2024

  44. [44]

    Ramchurn, and Mohammad D

    William Hunt, Sarvapali D. Ramchurn, and Mohammad D. Soorati. A Sur- vey of Language-Based Communication in Robotics. arXiv preprint arXiv:2406.04086, September 2024

    work page arXiv 2024

  45. [45]

    A survey of robot intelligence with large language models

    Hyeongyo Jeong, Haechan Lee, Changwon Kim, and Sungtae Shin. A survey of robot intelligence with large language models. Applied Sciences, 14(19):8868, 2024

    work page 2024

  46. [46]

    Collision- and reachability-aware multi-robot control with grounded llm planners

    Jiabao Ji, Yongchao Chen, Yang Zhang, Ramana Rao Kompella, Chuchu Fan, Gaowen Liu, and Shiyu Chang. Collision- and reachability-aware multi-robot control with grounded llm planners. arXiv preprint arXiv:2505.20573, 2025

    work page arXiv 2025

  47. [47]

    Genswarm: Scalable multi-robot code-policy generation and deployment via language models

    Wenkang Ji, Huaben Chen, Mingyang Chen, Guobin Zhu, Lufeng Xu, Roderich Groß, Rui Zhou, Ming Cao, and Shiyu Zhao. Genswarm: Scalable multi-robot code-policy generation and deployment via language models. arXiv preprint arXiv:2503.23875, 2025

    work page arXiv 2025

  48. [48]

    Exploring spontaneous social interaction swarm robotics powered by large language models

    Yitao Jiang, Luyang Zhao, Alberto Quat- trini Li, Muhao Chen, and Devin Balkcom. Exploring spontaneous social interaction swarm robotics powered by large language models

    work page

  49. [49]

    Principled approaches to the design of multi-robot systems

    Chris Jones, Dylan Shell, Maja J Mataric, and Brian Gerkey. Principled approaches to the design of multi-robot systems. In Proc. of the Workshop on Networked Robotics, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2004), 2004

    work page 2004

  50. [50]

    Shyam Sundar Kannan, Vishnunandan L. N. Venkatesh, and Byung-Cheol Min. SMART-LLM: Smart Multi-Agent Robot 26 Task Planning using Large Language Mod- els. arXiv preprint arXiv:2309.10062, March 2024

    work page arXiv 2024

  51. [51]

    Real-World Robot Applications of Foun- dation Models: A Review

    Kento Kawaharazuka, Tatsuya Mat- sushima, Andrew Gambardella, Jiaxian Guo, Chris Paxton, and Andy Zeng. Real-World Robot Applications of Foun- dation Models: A Review. arXiv preprint arXiv:2402.05741, October 2024

    work page arXiv 2024

  52. [52]

    OpenVLA: An Open-Source Vision-Language-Action Model

    Moo Jin Kim, Karl Pertsch, Siddharth Karamcheti, Ted Xiao, Ashwin Balakrishna, Suraj Nair, Rafael Rafailov, Ethan Fos- ter, Grace Lam, Pannag Sanketi, Quan Vuong, Thomas Kollar, Benjamin Burchfiel, Russ Tedrake, Dorsa Sadigh, Sergey Levine, Percy Liang, and Chelsea Finn. OpenVLA: An Open-Source Vision-Language-Action Model. arXiv preprint arXiv:2406.09246...

    work page internal anchor Pith review Pith/arXiv arXiv 2024

  53. [53]

    A Survey on Integration of Large Lan- guage Models with Intelligent Robots.arXiv preprint arXiv:2404.09228, August 2024

    Yeseung Kim, Dohyun Kim, Jieun Choi, Jisang Park, Nayoung Oh, and Daehyung Park. A Survey on Integration of Large Lan- guage Models with Intelligent Robots.arXiv preprint arXiv:2404.09228, August 2024

    work page arXiv 2024

  54. [54]

    AI2-THOR: An Interactive 3D Environment for Visual AI

    Eric Kolve, Roozbeh Mottaghi, Winson Han, Eli VanderBilt, Luca Weihs, Alvaro Herrasti, Daniel Gordon, Yuke Zhu, Abhi- nav Gupta, and Ali Farhadi. AI2-THOR: An Interactive 3D Environment for Visual AI. arXiv, 2017

    work page 2017

  55. [55]

    Oppor- tunities and challenges with autonomous micro aerial vehicles

    Vijay Kumar and Nathan Michael. Oppor- tunities and challenges with autonomous micro aerial vehicles. The International Journal of Robotics Research, 31(11):1279– 1291, 2012

    work page 2012

  56. [56]

    Exploring Large Language Mod- els to Facilitate Variable Autonomy for Human-Robot Teaming

    Younes Lakhnati, Max Pascher, and Jens Gerken. Exploring Large Language Mod- els to Facilitate Variable Autonomy for Human-Robot Teaming. arXiv preprint arXiv:2312.07214, March 2024

    work page arXiv 2024

  57. [57]

    Robotkube: Orchestrating large-scale cooperative multi- robot systems with kubernetes and ros

    Bastian Lampe, Lennart Reiher, Lukas Zanger, Timo Woopen, Raphael van Kem- pen, and Lutz Eckstein. Robotkube: Orchestrating large-scale cooperative multi- robot systems with kubernetes and ros. In 2023 IEEE 26th International Conference on Intelligent Transportation Systems (ITSC), pages 2719–2725. IEEE, 2023

    work page 2023

  58. [58]

    Retrieval-augmented generation for knowledge-intensive nlp tasks

    Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich K¨ uttler, Mike Lewis, Wen-tau Yih, Tim Rockt¨ aschel, et al. Retrieval-augmented generation for knowledge-intensive nlp tasks. Advances in Neural Information Processing Systems, 33:9459–9474, 2020

    work page 2020

  59. [59]

    Behavior-1k: A benchmark for embodied ai with 1,000 everyday activities and realistic simulation

    Chengshu Li, Ruohan Zhang, Josiah Wong, Cem Gokmen, Sanjana Srivastava, Roberto Mart´ ın-Mart´ ın, Chen Wang, Gabrael Levine, Michael Lingelbach, Jiankai Sun, et al. Behavior-1k: A benchmark for embodied ai with 1,000 everyday activities and realistic simulation. In Conference on Robot Learning, pages 80–93. PMLR, 2023

    work page 2023

  60. [60]

    Failure-aware multi-robot coordination for resilient and adap- tive target tracking

    Peihan Li, Jiazhen Liu, Yuwei Wu, and Lifeng Zhou. Failure-aware multi-robot coordination for resilient and adap- tive target tracking. arXiv preprint arXiv:2508.02529, 2025

    work page arXiv 2025

  61. [61]

    Challenges Faced by Large Language Models in Solving Multi-Agent Flocking

    Peihan Li, Vishnu Menon, Bhavanaraj Gudiguntla, Daniel Ting, and Lifeng Zhou. Challenges Faced by Large Language Models in Solving Multi-Agent Flocking. Distributed Autonomous Robotics Systems (DARS), April 2024

    work page 2024

  62. [62]

    Resilient and adaptive replanning for multi-robot target tracking with sens- ing and communication danger zones

    Peihan Li, Yuwei Wu, Jiazhen Liu, Gau- rav S Sukhatme, Vijay Kumar, and Lifeng Zhou. Resilient and adaptive replanning for multi-robot target tracking with sens- ing and communication danger zones. arXiv preprint arXiv:2409.11230, 2024

    work page arXiv 2024

  63. [63]

    Assign- ment algorithms for multi-robot multi- target tracking with sufficient and limited sensing capability

    Peihan Li and Lifeng Zhou. Assign- ment algorithms for multi-robot multi- target tracking with sufficient and limited sensing capability. In 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pages 11035– 11041. IEEE, 2023

    work page 2023

  64. [64]

    Llm-flock: Decentralized multi-robot flocking via large 27 language models and influence-based con- sensus

    Peihan Li and Lifeng Zhou. Llm-flock: Decentralized multi-robot flocking via large 27 language models and influence-based con- sensus. arXiv preprint arXiv:2505.06513, 2025

    work page arXiv 2025

  65. [65]

    Multimodal alignment and fusion: A survey

    Songtao Li and Hao Tang. Multimodal alignment and fusion: A survey. arXiv preprint arXiv:2411.17040, 2024

    work page arXiv 2024

  66. [66]

    Hmcf: A human-in-the-loop multi- robot collaboration framework based on large language models

    Zhaoxing Li, Wenbo Wu, Yue Wang, Yan- ran Xu, William Hunt, and Sebastian Stein. Hmcf: A human-in-the-loop multi- robot collaboration framework based on large language models. arXiv preprint arXiv:2505.00820, 2025

    work page arXiv 2025

  67. [67]

    A mechanism for scheduling multi robot intelligent warehouse system face with dynamic demand

    Zhi Li, Ali Vatankhah Barenji, Jiazhi Jiang, Ray Y Zhong, and Gangyan Xu. A mechanism for scheduling multi robot intelligent warehouse system face with dynamic demand. Journal of Intelligent Manufacturing, 31:469–480, 2020

    work page 2020

  68. [68]

    Integrating retrospective framework in multi-robot collaboration

    Jiazhao Liang, Hao Huang, Yu Hao, Geeta Chandra Raju Bethala, Congcong Wen, and Yi Fang. Integrating retrospective framework in multi-robot collaboration. In 2025 11th International Conference on Automation, Robotics, and Applications (ICARA), pages 195–199. IEEE, 2025

    work page 2025

  69. [69]

    Dynamic task adaptation for multi-robot manufac- turing systems with large language models

    Jonghan Lim and Ilya Kovalenko. Dynamic task adaptation for multi-robot manufac- turing systems with large language models. arXiv preprint arXiv:2505.22804, 2025

    work page arXiv 2025

  70. [70]

    DeepSeek-V3 Technical Report

    Aixin Liu, Bei Feng, Bing Xue, Bingxuan Wang, Bochao Wu, Chengda Lu, Cheng- gang Zhao, Chengqi Deng, Chenyu Zhang, Chong Ruan, et al. Deepseek-v3 techni- cal report. arXiv preprint arXiv:2412.19437, 2024

    work page internal anchor Pith review Pith/arXiv arXiv 2024

  71. [71]

    Multi-robot target tracking with sensing and communication danger zones

    Jiazhen Liu, Peihan Li, Yuwei Wu, Gau- rav S Sukhatme, Vijay Kumar, and Lifeng Zhou. Multi-robot target tracking with sensing and communication danger zones. Distributed Autonomous Robotic Systems (DARS), 2024

    work page 2024

  72. [72]

    Decentralized risk-aware tracking of multiple targets

    Jiazhen Liu, Lifeng Zhou, Ragesh Ramachandran, Gaurav S Sukhatme, and Vijay Kumar. Decentralized risk-aware tracking of multiple targets. InInternational Symposium on Distributed Autonomous Robotic Systems, pages 408–423. Springer, 2022

    work page 2022

  73. [73]

    Distributed resilient sub- modular action selection in adversarial envi- ronments

    Jun Liu, Lifeng Zhou, Pratap Tokekar, and Ryan K Williams. Distributed resilient sub- modular action selection in adversarial envi- ronments. IEEE Robotics and Automation Letters, 6(3):5832–5839, 2021

    work page 2021

  74. [74]

    COHERENT: Collaboration of Heterogeneous Multi-Robot System with Large Language Models

    Kehui Liu, Zixin Tang, Dong Wang, Zhigang Wang, Bin Zhao, and Xue- long Li. COHERENT: Collaboration of Heterogeneous Multi-Robot System with Large Language Models. arXiv preprint arXiv:2409.15146, September 2024

    work page arXiv 2024

  75. [75]

    Active metric-semantic mapping by multiple aerial robots

    Xu Liu, Ankit Prabhu, Fernando Cladera, Ian D Miller, Lifeng Zhou, Camillo J Taylor, and Vijay Kumar. Active metric-semantic mapping by multiple aerial robots. In 2023 IEEE International Conference on Robotics and Automation (ICRA), pages 3282–3288. IEEE, 2023

    work page 2023

  76. [76]

    BOLAA: Benchmark- ing and Orchestrating LLM-augmented Autonomous Agents

    Zhiwei Liu, Weiran Yao, Jianguo Zhang, Le Xue, Shelby Heinecke, Rithesh Murthy, Yihao Feng, Zeyuan Chen, Juan Carlos Niebles, Devansh Arpit, Ran Xu, Phil Mui, Huan Wang, Caiming Xiong, and Silvio Savarese. BOLAA: Benchmark- ing and Orchestrating LLM-augmented Autonomous Agents. arXiv preprint arXiv:2308.05960, August 2023

    work page arXiv 2023

  77. [77]

    Efficient and complete centralized multi-robot path planning

    Ryan Luna and Kostas E Bekris. Efficient and complete centralized multi-robot path planning. In 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems, pages 3268–3275. IEEE, 2011

    work page 2011

  78. [78]

    Multi-robot search and rescue team

    Cai Luo, Andre Possani Espinosa, Danu Pranantha, and Alessandro De Gloria. Multi-robot search and rescue team. In2011 IEEE International Symposium on Safety, Security, and Rescue Robotics, pages 296–

    work page

  79. [79]

    LLM- MARS: Large Language Model for Behavior Tree Generation and NLP-enhanced Dia- logue in Multi-Agent Robot Systems

    Artem Lykov, Maria Dronova, Nikolay Naglov, Mikhail Litvinov, Sergei Satsevich, Artem Bazhenov, Vladimir Berman, Aleksei 28 Shcherbak, and Dzmitry Tsetserukou. LLM- MARS: Large Language Model for Behavior Tree Generation and NLP-enhanced Dia- logue in Multi-Agent Robot Systems. arXiv preprint arXiv:2312.09348, December 2023

    work page arXiv 2023

  80. [80]

    Flockgpt: Guiding uav flocking with linguistic orchestration

    Artem Lykov, Sausar Karaf, Mikhail Mar- tynov, Valerii Serpiva, Aleksey Fedoseev, Mikhail Konenkov, and Dzmitry Tset- serukou. Flockgpt: Guiding uav flocking with linguistic orchestration. arXiv preprint arXiv:2405.05872, 2024

    work page arXiv 2024

Showing first 80 references.