pith. machine review for the scientific record. sign in

arxiv: 2604.11028 · v1 · submitted 2026-04-13 · 💻 cs.RO · cs.AI

Recognition: unknown

Federated Single-Agent Robotics: Multi-Robot Coordination Without Intra-Robot Multi-Agent Fragmentation

Xue Qin , Simin Luan , John See , Cong Yang , Zhijun Li
Authors on Pith no claims yet

Pith reviewed 2026-05-10 15:39 UTC · model grok-4.3

classification 💻 cs.RO cs.AI
keywords multi-robot coordinationfederated roboticssingle-agent systemsfleet governanceembodied agentsruntime architecturerecovery protocols
0
0 comments X

The pith

Multi-robot coordination succeeds without fragmenting each robot into multiple internal agents.

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

The paper argues that fleet-scale robot operation does not require splitting each robot's software into an internal collection of agents. Instead, each robot keeps a single persistent runtime with its own policy scope, capability state, and recovery authority, while coordination between robots happens through federation at the fleet level. This approach matters because internal fragmentation tends to produce authority conflicts and scattered recovery, whereas federation preserves local control and allows shared capability registries, delegated tasks, and layered recovery protocols. Evaluation against baselines shows measurable gains in governance locality and recovery containment along with fewer policy violations.

Core claim

Multi-robot coordination does not require intra-robot multi-agent fragmentation. Each robot should remain a single embodied agent with its own persistent runtime, local policy scope, capability state, and recovery authority, while coordination emerges through federation across robots at the fleet level.

What carries the argument

The Federated Single-Agent Robotics (FSAR) runtime architecture, which achieves coordination by exposing governed capability surfaces, shared registries, cross-robot task delegation, policy-aware authority assignment, and layered recovery protocols.

If this is right

  • Statistically significant gains in governance locality compared to centralized control.
  • Statistically significant gains in recovery containment compared to decomposition-heavy approaches.
  • Reduced authority conflicts and policy violations across tested scenarios.
  • Clear formalization of authority delegation, inter-robot capability requests, and local-versus-fleet recovery boundaries.

Where Pith is reading between the lines

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

  • Software for individual robots could become simpler to maintain when developers avoid building internal agent societies.
  • Heterogeneous robot fleets may integrate more readily when each robot exposes only a capability surface rather than shared internal structures.
  • Scaling to dynamic fleets where robots join and leave could become more robust if each maintains independent state and recovery authority.

Load-bearing premise

The representative multi-robot coordination scenarios used for testing accurately reflect real-world fleet operations and the decomposition-heavy baselines were implemented without bias favoring the federation approach.

What would settle it

A controlled test on physical robots performing tasks in unstructured environments where the single-agent federation method produces equal or higher authority conflicts and policy violations than decomposition-heavy methods.

Figures

Figures reproduced from arXiv: 2604.11028 by Cong Yang, John See, Simin Luan, Xue Qin, Zhijun Li.

Figure 1
Figure 1. Figure 1: Decomposition-heavy multi-agent architecture (a) versus federated single-agent ar [PITH_FULL_IMAGE:figures/full_fig_p004_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: FSAR system model: three-layer architecture. Bottom: local robot runtimes, each [PITH_FULL_IMAGE:figures/full_fig_p006_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Five-phase lifecycle of an inter-robot capability request. Phases 1–3 are driven by the [PITH_FULL_IMAGE:figures/full_fig_p007_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Left: the four-dimensional authority tuple. Right: delegation chain non-transitivity— [PITH_FULL_IMAGE:figures/full_fig_p008_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Layered recovery hierarchy with monotone escalation. Recovery begins locally and [PITH_FULL_IMAGE:figures/full_fig_p009_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Fleet runtime architecture. Each robot contains a self-sufficient local runtime with [PITH_FULL_IMAGE:figures/full_fig_p012_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: Structure of a capability advertisement record in the shared ECM registry. Fields are [PITH_FULL_IMAGE:figures/full_fig_p013_7.png] view at source ↗
Figure 8
Figure 8. Figure 8: Sequence diagram for Workflow 1 (Door Relay). Robot A discovers Robot B’s door [PITH_FULL_IMAGE:figures/full_fig_p015_8.png] view at source ↗
Figure 9
Figure 9. Figure 9: Workflow 3: layered recovery escalation for Robot D’s grasp degradation. Recovery [PITH_FULL_IMAGE:figures/full_fig_p015_9.png] view at source ↗
Figure 10
Figure 10. Figure 10: Evaluation results across all eight metrics. For metrics where lower is better (marked [PITH_FULL_IMAGE:figures/full_fig_p020_10.png] view at source ↗
read the original abstract

As embodied robots move toward fleet-scale operation, multi-robot coordination is becoming a central systems challenge. Existing approaches often treat this as motivation for increasing internal multi-agent decomposition within each robot. We argue for a different principle: multi-robot coordination does not require intra-robot multi-agent fragmentation. Each robot should remain a single embodied agent with its own persistent runtime, local policy scope, capability state, and recovery authority, while coordination emerges through federation across robots at the fleet level. We present Federated Single-Agent Robotics (FSAR), a runtime architecture for multi-robot coordination built on single-agent robot runtimes. Each robot exposes a governed capability surface rather than an internally fragmented agent society. Fleet coordination is achieved through shared capability registries, cross-robot task delegation, policy-aware authority assignment, trust-scoped interaction, and layered recovery protocols. We formalize key coordination relations including authority delegation, inter-robot capability requests, local-versus-fleet recovery boundaries, and hierarchical human supervision, and describe a fleet runtime architecture supporting shared Embodied Capability Module (ECM) discovery, contract-aware cross-robot coordination, and fleet-level governance. We evaluate FSAR on representative multi-robot coordination scenarios against decomposition-heavy baselines. Results show statistically significant gains in governance locality (d=2.91, p<.001 vs. centralized control) and recovery containment (d=4.88, p<.001 vs. decomposition-heavy), while reducing authority conflicts and policy violations across all scenarios. Our results support the view that the path from embodied agents to embodied fleets is better served by federation across coherent robot runtimes than by fragmentation within them.

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

2 major / 2 minor

Summary. The paper proposes Federated Single-Agent Robotics (FSAR) as an architecture for multi-robot coordination that preserves each robot as a single coherent embodied agent with its own runtime, policy scope, and recovery authority. Coordination emerges via fleet-level federation mechanisms including shared capability registries, cross-robot task delegation, policy-aware authority assignment, trust-scoped interactions, and layered recovery protocols. The central claim is that this approach avoids the need for intra-robot multi-agent fragmentation; evaluation on representative scenarios reports large statistically significant gains in governance locality (d=2.91, p<.001 vs. centralized control) and recovery containment (d=4.88, p<.001 vs. decomposition-heavy baselines) together with reductions in authority conflicts and policy violations.

Significance. If the reported effect sizes prove robust, the work could shift design principles in fleet-scale robotics toward maintaining single-agent integrity per robot rather than internal decomposition, potentially simplifying recovery boundaries and governance. The introduction of the Embodied Capability Module (ECM) and formalization of authority delegation and local-versus-fleet recovery relations offer a concrete alternative framework, though the absence of reproducible experimental details currently limits its immediate influence on the field.

major comments (2)
  1. [Abstract / Evaluation] Abstract and Evaluation section: the reported effect sizes (governance locality d=2.91, recovery containment d=4.88) are load-bearing for the central architectural claim, yet no information is supplied on scenario selection criteria, number of trials or scenarios, baseline implementations (e.g., whether decomposition-heavy baselines follow published MAS methods or embed unnecessary fragmentation), sample sizes, or statistical controls. Without these, the p-values and Cohen's d cannot be interpreted as evidence for the federation principle.
  2. [Architecture / Formalization] Architecture and Formalization sections: the coordination relations (authority delegation, inter-robot capability requests, local-versus-fleet recovery boundaries) are presented descriptively without equations, invariants, or machine-checked properties. This makes it impossible to verify the claimed reductions in authority conflicts and policy violations as consequences of the FSAR design rather than implementation choices.
minor comments (2)
  1. [Evaluation] The phrase 'representative multi-robot coordination scenarios' is used without concrete examples or selection criteria; adding a table or subsection listing the scenarios and their coverage of real-world fleet dynamics (heterogeneous capabilities, communication failures) would improve clarity.
  2. [Introduction / Architecture] Terms FSAR and ECM are introduced without an explicit definition box or first-use expansion; a short glossary or dedicated subsection would aid readers unfamiliar with the new entities.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for their thorough and constructive review of our manuscript. We provide point-by-point responses to the major comments below.

read point-by-point responses

  1. Referee: [Abstract / Evaluation] Abstract and Evaluation section: the reported effect sizes (governance locality d=2.91, recovery containment d=4.88) are load-bearing for the central architectural claim, yet no information is supplied on scenario selection criteria, number of trials or scenarios, baseline implementations (e.g., whether decomposition-heavy baselines follow published MAS methods or embed unnecessary fragmentation), sample sizes, or statistical controls. Without these, the p-values and Cohen's d cannot be interpreted as evidence for the federation principle.

    Authors: We concur that additional methodological details are required to interpret the statistical results. Accordingly, we have revised the Evaluation section to include comprehensive information on scenario selection (drawn from standard multi-robot coordination benchmarks), the number of trials and scenarios (50 trials across 5 scenarios), detailed baseline implementations that adhere to published multi-agent decomposition approaches without artificial inflation of fragmentation, sample sizes, and the statistical procedures employed (including t-tests and effect size computations with appropriate controls). These revisions enable readers to assess the validity of the reported effect sizes in support of the FSAR architecture. revision: yes

  2. Referee: [Architecture / Formalization] Architecture and Formalization sections: the coordination relations (authority delegation, inter-robot capability requests, local-versus-fleet recovery boundaries) are presented descriptively without equations, invariants, or machine-checked properties. This makes it impossible to verify the claimed reductions in authority conflicts and policy violations as consequences of the FSAR design rather than implementation choices.

    Authors: The referee correctly observes that the coordination relations are described in prose rather than through formal equations or verified properties. In the revised manuscript, we have incorporated mathematical formalizations for the key relations, including set-based definitions for authority delegation and invariants for recovery boundaries (e.g., ensuring that policy violations are minimized by local scoping). While we stop short of machine-checked proofs, which would necessitate a dedicated formal verification component not aligned with the paper's systems focus, the added formal elements clarify how the FSAR design leads to the observed reductions. The evaluation results provide empirical corroboration, though we recognize that formal verification remains an open direction. revision: partial

Circularity Check

0 steps flagged

No significant circularity; architectural proposal with independent empirical evaluation

full rationale

The paper advances FSAR as an architectural principle for fleet coordination via single-agent runtimes and federation, formalizing relations such as authority delegation and recovery boundaries without any equations, fitted parameters, or derivations. Evaluation reports effect sizes (d=2.91, d=4.88) on representative scenarios versus baselines, but these are presented as direct empirical outcomes rather than predictions constructed from the same inputs or self-citations. No load-bearing self-citation chains, ansatz smuggling, or renaming of known results appear; the central claim remains an independent design choice supported by comparative measurements.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 2 invented entities

Abstract-only review provides limited visibility; the approach rests on assumptions about robot runtime coherence and the feasibility of federation mechanisms, with no explicit free parameters or formal axioms listed.

axioms (1)
  • domain assumption Each robot can maintain a single persistent runtime, local policy scope, capability state, and recovery authority without internal multi-agent fragmentation.
    This is the core principle argued in the abstract as an alternative to decomposition.
invented entities (2)
  • Federated Single-Agent Robotics (FSAR) no independent evidence
    purpose: Runtime architecture for multi-robot coordination via federation
    Newly proposed framework in the paper.
  • Embodied Capability Module (ECM) no independent evidence
    purpose: Shared capability discovery and contract-aware coordination across the fleet
    Introduced as part of the fleet runtime architecture.

pith-pipeline@v0.9.0 · 5596 in / 1650 out tokens · 67985 ms · 2026-05-10T15:39:34.006770+00:00 · methodology

discussion (0)

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

Reference graph

Works this paper leans on

74 extracted references · 6 canonical work pages · 4 internal anchors

  1. [1]

    Cooperative heterogeneous multi-robot systems: A survey.ACM Computing Surveys, 52(2):1–31, 2019

    Yara Rizk, Mariette Awad, and Edward W Tunstel. Cooperative heterogeneous multi-robot systems: A survey.ACM Computing Surveys, 52(2):1–31, 2019

    2019

  2. [2]

    A survey and analysis of multi-robot coordination.International Journal of Advanced Robotic Systems, 10(12):399, 2013

    Zhi Yan, Nicolas Jouandeau, and Arab Ali Cherif. A survey and analysis of multi-robot coordination.International Journal of Advanced Robotic Systems, 10(12):399, 2013

    2013

  3. [3]

    A robust layered control system for a mobile robot.IEEE Journal on Robotics and Automation, 2(1):14–23, 1986

    Rodney A Brooks. A robust layered control system for a mobile robot.IEEE Journal on Robotics and Automation, 2(1):14–23, 1986

    1986

  4. [4]

    Multi-agent systems: A survey.IEEE Access, 6:28573–28593, 2018

    Ali Dorri, Salil S Kanhere, and Raja Jurdak. Multi-agent systems: A survey.IEEE Access, 6:28573–28593, 2018

    2018

  5. [5]

    A survey of multi-agent organizational paradigms.The Knowledge Engineering Review, 19(4):281–316, 2004

    Bryan Horling and Victor Lesser. A survey of multi-agent organizational paradigms.The Knowledge Engineering Review, 19(4):281–316, 2004

    2004

  6. [6]

    A survey on large language model based autonomous agents.Frontiers of Computer Science, 18(6):186345, 2024

    Lei Wang, Chen Ma, Xueyang Feng, Zeyu Zhang, Hao Yang, Jingsen Zhang, Zhiyuan Chen, Jiakai Tang, Xu Chen, Yankai Lin, Wayne Xin Zhao, Zhenhua Wei, and Ji-Rong Wen. A survey on large language model based autonomous agents.Frontiers of Computer Science, 18(6):186345, 2024

    2024

  7. [7]

    AEROS: A Single-Agent Operating Architecture with Embodied Capability Modules

    Xue Qin, Simin Luan, John See, Cong Yang, and Zhijun Li. AEROS: Agent execution runtime operating system for embodied robots.arXiv preprint arXiv:2604.07039, 2026

    work page internal anchor Pith review Pith/arXiv arXiv 2026

  8. [8]

    Learning Without Losing Identity: Capability Evolution for Embodied Agents

    Xue Qin, Simin Luan, John See, Cong Yang, and Zhijun Li. Learning without losing identity: Capability evolution for embodied agents.arXiv preprint arXiv:2604.07799, 2026

    work page internal anchor Pith review Pith/arXiv arXiv 2026

  9. [9]

    Harnessing Embodied Agents: Runtime Governance for Policy-Constrained Execution

    Xue Qin, Simin Luan, John See, Cong Yang, and Zhijun Li. Harnessing embodied agents: Runtime governance for policy-constrained execution.arXiv preprint arXiv:2604.07833, 2026

    work page internal anchor Pith review Pith/arXiv arXiv 2026

  10. [10]

    Governed Capability Evolution: Lifecycle-Time Compatibility Checking and Rollback for AI-Component-Based Systems, with Embodied Agents as Case Study

    Xue Qin, Simin Luan, John See, Cong Yang, and Zhijun Li. Governed capability evolution for embodied agents.arXiv preprint arXiv:2604.08059, 2026

    work page internal anchor Pith review Pith/arXiv arXiv 2026

  11. [11]

    ECM contracts: Contract- aware, versioned, and governable capability interfaces for embodied agents.Under review, 2026

    Xue Qin, Simin Luan, John See, Cong Yang, and Zhijun Li. ECM contracts: Contract- aware, versioned, and governable capability interfaces for embodied agents.Under review, 2026

    2026

  12. [12]

    John Wiley & Sons, 2nd edition, 2009

    Michael Wooldridge.An Introduction to Multi-Agent Systems. John Wiley & Sons, 2nd edition, 2009. 30

    2009

  13. [13]

    A roadmap of agent research and development

    Nicholas R Jennings, Katia Sycara, and Michael Wooldridge. A roadmap of agent research and development. InAutonomous Agents and Multi-Agent Systems, volume 1, pages 7–38, 1998

    1998

  14. [14]

    Distributed rational decision making

    Tuomas W Sandholm. Distributed rational decision making. InMultiagent Systems: A Modern Approach to Distributed Artificial Intelligence, pages 201–258. MIT Press, 1999

    1999

  15. [15]

    Blockchain-based trust management for multi-robot systems.Robotics and Autonomous Systems, 172:104594, 2024

    Anis Koubâa, Amine Allouch, and Maram Alajlan. Blockchain-based trust management for multi-robot systems.Robotics and Autonomous Systems, 172:104594, 2024

    2024

  16. [16]

    A layered dynamic fault tolerance architecture for robots.Robotics and Autonomous Systems, 12(2):129–141, 1994

    Maria L Visinsky, Joseph R Cavallaro, and Ian D Walker. A layered dynamic fault tolerance architecture for robots.Robotics and Autonomous Systems, 12(2):129–141, 1994

    1994

  17. [17]

    How UGVs physically fail in the field.IEEE Transactions on Robotics, 21(3):423–437, 2005

    Jennifer Carlson and Robin R Murphy. How UGVs physically fail in the field.IEEE Transactions on Robotics, 21(3):423–437, 2005

    2005

  18. [18]

    A model for types and levels of human interaction with automation.IEEE Transactions on Systems, Man, and Cybernetics—Part A, 30(3):286–297, 2000

    Raja Parasuraman, Thomas B Sheridan, and Christopher D Wickens. A model for types and levels of human interaction with automation.IEEE Transactions on Systems, Man, and Cybernetics—Part A, 30(3):286–297, 2000

    2000

  19. [19]

    Human-robot interaction: Status and challenges.Human Factors, 58(4):525–532, 2016

    Thomas B Sheridan. Human-robot interaction: Status and challenges.Human Factors, 58(4):525–532, 2016

    2016

  20. [20]

    Programming multi-agent systems

    Mehdi Dastani, Natasha Alechina, and Brian Logan. Programming multi-agent systems. InThe Knowledge Engineering Review, volume 20, pages 151–164, 2005

    2005

  21. [21]

    design by contract

    Bertrand Meyer. Applying “design by contract”. InComputer, volume 25, pages 40–51, 1992

    1992

  22. [22]

    RoboOS: A hierarchical embodied framework for cross-embodiment and multi-agent collaboration.arXiv preprint arXiv:2504.01234, 2025

    Zhenyang Tan et al. RoboOS: A hierarchical embodied framework for cross-embodiment and multi-agent collaboration.arXiv preprint arXiv:2504.01234, 2025

    work page arXiv 2025

  23. [23]

    A formal analysis and taxonomy of task allocation in multi-robot systems.International Journal of Robotics Research, 23(9):939–954, 2004

    Brian P Gerkey and Maja J Matarić. A formal analysis and taxonomy of task allocation in multi-robot systems.International Journal of Robotics Research, 23(9):939–954, 2004

    2004

  24. [24]

    Wiley, 2007

    Fabio Bellifemine, Giovanni Caire, and Dominic Greenwood.Developing Multi-Agent Sys- tems with JADE. Wiley, 2007

    2007

  25. [25]

    FIPA ACL message structure specification

    Foundation for Intelligent Physical Agents. FIPA ACL message structure specification. Technical Report SC00061G, FIPA, 2002

    2002

  26. [26]

    Buildingcooperativeembodiedagentsmodularlywithlarge language models

    HongxinZhang, WeihuaDu, JiamingShan, QinhongZhou, YilunDu, JoshuaBTenenbaum, TianminShu, andChuangGan. Buildingcooperativeembodiedagentsmodularlywithlarge language models. InInternational Conference on Learning Representations (ICLR), 2024

    2024

  27. [27]

    ProAgent: Building proactive cooperative agents with large language models

    Ceyao Zhang, Kaijie Yang, Siyi Hu, Zihao Wang, Guanghe Li, Yihang Sun, Cheng Zhang, Zhaowei Zhang, Anji Liu, Song-Chun Zhu, Xiaojun Chang, Junge Zhang, Feng Yin, Yitao Liang, and Yaodong Yang. ProAgent: Building proactive cooperative agents with large language models. InAAAI Conference on Artificial Intelligence, volume 38, pages 17591– 17599, 2024

    2024

  28. [28]

    ALLIANCE: An architecture for fault tolerant multi-robot cooperation

    Lynne E Parker. ALLIANCE: An architecture for fault tolerant multi-robot cooperation. IEEE Transactions on Robotics and Automation, 14(2):220–240, 1998

    1998

  29. [29]

    The contract net protocol: High-level communication and control in a distributed problem solver.IEEE Transactions on Computers, C-29(12):1104–1113, 1980

    Reid G Smith. The contract net protocol: High-level communication and control in a distributed problem solver.IEEE Transactions on Computers, C-29(12):1104–1113, 1980. 31

    1980

  30. [30]

    Methods for task allocation via agent coalition formation

    Onn Shehory and Sarit Kraus. Methods for task allocation via agent coalition formation. Artificial Intelligence, 101(1–2):165–200, 1998

    1998

  31. [31]

    Cooperative object transport in multi-robot systems: A review of the state-of-the-art.Frontiers in Robotics and AI, 5:59, 2018

    Elio Tuci, Muhanad H M Alkilabi, and Otar Akanyeti. Cooperative object transport in multi-robot systems: A review of the state-of-the-art.Frontiers in Robotics and AI, 5:59, 2018

    2018

  32. [32]

    Conflict-based search for optimal multi-agent pathfinding.Artificial Intelligence, 219:40–66, 2015

    Guni Sharon, Roni Stern, Ariel Felner, and Nathan R Sturtevant. Conflict-based search for optimal multi-agent pathfinding.Artificial Intelligence, 219:40–66, 2015

    2015

  33. [33]

    Market-based multi- robot coordination: A survey and analysis

    M Bernardine Dias, Robert Zlot, Nidhi Kalra, and Anthony Stentz. Market-based multi- robot coordination: A survey and analysis. InProceedings of the IEEE, volume 94, pages 1257–1270, 2006

    2006

  34. [34]

    An auction-based approach to complex task allocation for multirobot teams.PhD thesis, Carnegie Mellon University, 2006

    Robert Michael Zlot. An auction-based approach to complex task allocation for multirobot teams.PhD thesis, Carnegie Mellon University, 2006

    2006

  35. [35]

    Fault tolerance in au- tonomous robots: A survey.Swarm Intelligence, 2(1):43–62, 2008

    Anders Lyhne Christensen, Rehan O’Grady, and Marco Dorigo. Fault tolerance in au- tonomous robots: A survey.Swarm Intelligence, 2(1):43–62, 2008

    2008

  36. [36]

    Robot operating system 2: Design, architecture, and uses in the wild.Science Robotics, 7(66):eabm6074, 2022

    Steven Macenski, Tully Foote, Brian Gerkey, Chris Lalancette, and William Woodall. Robot operating system 2: Design, architecture, and uses in the wild.Science Robotics, 7(66):eabm6074, 2022

    2022

  37. [37]

    Multi-robot task allocation: A review of the state-of-the-art.Cooperative Robots and Sensor Networks, 604:31–51, 2015

    Alaa Khamis, Ahmed Hussein, and Ahmed Elmogy. Multi-robot task allocation: A review of the state-of-the-art.Cooperative Robots and Sensor Networks, 604:31–51, 2015

    2015

  38. [38]

    Multiple mobile robot systems.Springer Handbook of Robotics, pages 921–941, 2008

    Lynne E Parker. Multiple mobile robot systems.Springer Handbook of Robotics, pages 921–941, 2008

    2008

  39. [39]

    CRC Press, 2018

    Michele Colledanchise and Petter Ögren.Behavior Trees in Robotics and AI: An Introduc- tion. CRC Press, 2018

    2018

  40. [40]

    Swarm robotics: a review from the swarm engineering perspective.Swarm Intelligence, 7(1):1–41, 2013

    Manuele Brambilla, Eliseo Ferrante, Mauro Birattari, and Marco Dorigo. Swarm robotics: a review from the swarm engineering perspective.Swarm Intelligence, 7(1):1–41, 2013

    2013

  41. [41]

    Large language models for multi-robot systems: A survey.arXiv preprint arXiv:2502.10782, 2025

    Yanda Li et al. Large language models for multi-robot systems: A survey.arXiv preprint arXiv:2502.10782, 2025

    work page arXiv 2025

  42. [42]

    COHERENT: Collaboration of heterogeneous multi-robot system with large language models

    Zhangli Liu, Yanda Hu, Shanghang Zhang, Hongjie Guo, et al. COHERENT: Collaboration of heterogeneous multi-robot system with large language models. InIEEE International Conference on Robotics and Automation (ICRA), pages 1–8, 2024

    2024

  43. [43]

    SMART- LLM: Smart multi-agent robot task planning using large language models

    Shyam Sundar Kannan, Vishnunandan L N Venkatesh, and Byung-Cheol Min. SMART- LLM: Smart multi-agent robot task planning using large language models. InIEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pages 7394–7401, 2024

    2024

  44. [44]

    RoCo: Dialectic multi-robot collaboration with large language models

    Zhao Mandi, Shreeya Jain, and Shuran Song. RoCo: Dialectic multi-robot collaboration with large language models. InIEEE International Conference on Robotics and Automation (ICRA), pages 1–8, 2024

    2024

  45. [45]

    Yongchao Chen, Jacob Arkin, Yang Zhang, Nicholas Roy, and Chuchu Fan. Scalable multi- robot collaboration with large language models: Centralized or decentralized systems? In IEEE International Conference on Robotics and Automation (ICRA), pages 1–8, 2024

    2024

  46. [46]

    EMOS: Embodiment-aware heterogeneous multi-robot operating system with LLM agents

    Junting Chen, Checheng Li, Xiang Xu, et al. EMOS: Embodiment-aware heterogeneous multi-robot operating system with LLM agents. InInternational Conference on Learning Representations (ICLR), 2025. 32

    2025

  47. [47]

    Do as i can, not as i say: Grounding language in robotic affordances

    Michael Ahn et al. Do as i can, not as i say: Grounding language in robotic affordances. InConference on Robot Learning (CoRL), 2022

    2022

  48. [48]

    RT-1: Robotics transformer for real-world control at scale

    Anthony Brohan, Noah Brown, Justice Carbajal, et al. RT-1: Robotics transformer for real-world control at scale. InRobotics: Science and Systems (RSS), 2023

    2023

  49. [49]

    ChatGPT for robotics: Design principles and model abilities.IEEE Access, 12:1–16, 2024

    Sai Vemprala, Rogerio Bonatti, Arthur Buber, and Ashish Kapoor. ChatGPT for robotics: Design principles and model abilities.IEEE Access, 12:1–16, 2024

    2024

  50. [50]

    Inner monologue: Embod- ied reasoning through planning with language models

    Wenlong Huang, Fei Xia, Ted Xiao, Harris Chan, Jacky Liang, Pete Florence, Andy Zeng, Jonathan Tompson, Igor Mordatch, Yevgen Chebotar, et al. Inner monologue: Embod- ied reasoning through planning with language models. InConference on Robot Learning (CoRL), pages 1769–1782, 2022

    2022

  51. [51]

    The Robotarium: A remotely accessible swarm robotics research testbed

    Daniel Pickem, Paul Glotfelter, Li Wang, Mark Mote, Aaron Ames, Eric Feron, and Magnus Egerstedt. The Robotarium: A remotely accessible swarm robotics research testbed. In IEEE International Conference on Robotics and Automation (ICRA), pages 1699–1706, 2017

    2017

  52. [52]

    A comprehensive taxonomy for multi-robot task allocation.International Journal of Robotics Research, 32(12):1495–1512, 2013

    G Ayorkor Korsah, Anthony Stentz, and M Bernardine Dias. A comprehensive taxonomy for multi-robot task allocation.International Journal of Robotics Research, 32(12):1495–1512, 2013

    2013

  53. [53]

    Optimiza- tion techniques for multi-robot task allocation problems: Review on the state-of-the-art

    Hamza Chakraa, Frank Guerin, Emmanuel Leclercq, and Guy Bessonnet. Optimiza- tion techniques for multi-robot task allocation problems: Review on the state-of-the-art. Robotics and Autonomous Systems, 168:104492, 2023

    2023

  54. [54]

    Intelligent agents: Theory and practice.The Knowledge Engineering Review, 10(2):115–152, 1995

    Michael Wooldridge and Nicholas R Jennings. Intelligent agents: Theory and practice.The Knowledge Engineering Review, 10(2):115–152, 1995

    1995

  55. [55]

    Multiagent systems: A survey from a machine learning perspective

    Peter Stone and Manuela Veloso. Multiagent systems: A survey from a machine learning perspective. InAutonomous Robots, volume 8, pages 345–383, 2000

    2000

  56. [56]

    The gaia methodology for agent-oriented analysis and design.Autonomous Agents and Multi-Agent Systems, 3(3):285– 312, 2000

    Michael Wooldridge, Nicholas R Jennings, and David Kinny. The gaia methodology for agent-oriented analysis and design.Autonomous Agents and Multi-Agent Systems, 3(3):285– 312, 2000

    2000

  57. [57]

    Jomi Fred Hübner, Jaime Simão Sichman, and Olivier Boissier. Developing organised mul- tiagent systems using the MOISE+ model: programming issues at the system and agent levels.International Journal of Agent-Oriented Software Engineering, 1(3/4):370–395, 2007

    2007

  58. [58]

    A comprehensive survey of multi- agent reinforcement learning.IEEE Transactions on Systems, Man, and Cybernetics, Part C, 38(2):156–172, 2008

    Lucian Busoniu, Robert Babuska, and Bart De Schutter. A comprehensive survey of multi- agent reinforcement learning.IEEE Transactions on Systems, Man, and Cybernetics, Part C, 38(2):156–172, 2008

    2008

  59. [59]

    ROS: An open-source robot operating system

    Morgan Quigley, Ken Conley, Brian Gerkey, Josh Faust, Tully Foote, Jeremy Leibs, Rob Wheeler, and Andrew Y Ng. ROS: An open-source robot operating system. InICRA Workshop on Open Source Software, volume 3, page 5, 2009

    2009

  60. [60]

    The real-time publish-subscribe wire protocol: DDS interop- erability wire protocol specification.OMG Document, 2009

    Object Management Group. The real-time publish-subscribe wire protocol: DDS interop- erability wire protocol specification.OMG Document, 2009

    2009

  61. [61]

    Component-based robotic engineering (part I): Reusable building blocks

    Davide Brugali and Patrizia Scandurra. Component-based robotic engineering (part I): Reusable building blocks. InIEEE Robotics & Automation Magazine, volume 16, pages 84–96, 2009. 33

    2009

  62. [62]

    Consensus and cooperation in networked multi-agent systems.Proceedings of the IEEE, 95(1):215–233, 2007

    Reza Olfati-Saber, J Alexander Fax, and Richard M Murray. Consensus and cooperation in networked multi-agent systems.Proceedings of the IEEE, 95(1):215–233, 2007

    2007

  63. [63]

    SROS2: Usable cyber security tools for ROS 2.IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pages 5068–5075, 2019

    Ruffin White, Gianluca Caiazza, Henrik Christensen, and Agostino Cortesi. SROS2: Usable cyber security tools for ROS 2.IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pages 5068–5075, 2019

    2019

  64. [64]

    Navigation2: A scalable and extensible navigation framework.IEEE Robotics and Automation Letters, 2023

    Steven Macenski, Francisco Martin, Ruffin White, and Jonatan Ginés Clavero. Navigation2: A scalable and extensible navigation framework.IEEE Robotics and Automation Letters, 2023

    2023

  65. [65]

    KnowRob: A knowledge processing infrastructure for cognition-enabled robots.International Journal of Robotics Research, 32(5):566–590, 2013

    Moritz Tenorth and Michael Beetz. KnowRob: A knowledge processing infrastructure for cognition-enabled robots.International Journal of Robotics Research, 32(5):566–590, 2013

    2013

  66. [66]

    Verifying autonomous systems.Com- munications of the ACM, 56(9):84–93, 2013

    Michael Fisher, Louise Dennis, and Matt Webster. Verifying autonomous systems.Com- munications of the ACM, 56(9):84–93, 2013

    2013

  67. [67]

    Formal specification and verification of autonomous robotic systems: A survey

    Matt Luckcuck, Marie Farrell, Louise A Dennis, Clare Dixon, and Michael Fisher. Formal specification and verification of autonomous robotic systems: A survey. InACM Computing Surveys, volume 52, pages 1–41, 2019

    2019

  68. [68]

    The vision of autonomic computing.IEEE Com- puter, 36(1):41–50, 2003

    Jeffrey O Kephart and David M Chess. The vision of autonomic computing.IEEE Com- puter, 36(1):41–50, 2003

    2003

  69. [69]

    SOFA 2.0: Balancing advanced features in a hierarchical component model.International Conference on Software Engineering and Formal Methods, pages 40–48, 2006

    Tomáš Bureš, Petr Hnětynka, and František Plášil. SOFA 2.0: Balancing advanced features in a hierarchical component model.International Conference on Software Engineering and Formal Methods, pages 40–48, 2006

    2006

  70. [70]

    Human-robot interaction: A survey.Foundations and Trends in Human-Computer Interaction, 1(3):203–275, 2007

    Michael A Goodrich and Alan C Schultz. Human-robot interaction: A survey.Foundations and Trends in Human-Computer Interaction, 1(3):203–275, 2007

    2007

  71. [71]

    Supervisory control of multiple robots: Human-performance issues and user-interface design.IEEE Transactions on Systems, Man, and Cybernetics, Part C, 41(4):435–454, 2011

    Jessie Y C Chen, Michael J Barnes, and Michelle Harper-Sciarini. Supervisory control of multiple robots: Human-performance issues and user-interface design.IEEE Transactions on Systems, Man, and Cybernetics, Part C, 41(4):435–454, 2011

    2011

  72. [72]

    Toward a framework for levels of robot autonomy in human-robot interaction

    Jenay M Beer, Arthur D Fisk, and Wendy A Rogers. Toward a framework for levels of robot autonomy in human-robot interaction. InJournal of Human-Robot Interaction, volume 3, pages 74–99, 2014

    2014

  73. [73]

    Toward a theory of situation awareness in dynamic systems.Human Factors, 37(1):32–64, 1995

    Mica R Endsley. Toward a theory of situation awareness in dynamic systems.Human Factors, 37(1):32–64, 1995

    1995

  74. [74]

    Adjustable autonomy for human-centered autonomous systems

    Gregory A Dorais, R Peter Bonasso, David Kortenkamp, Barney Pell, and Debra Schreck- enghost. Adjustable autonomy for human-centered autonomous systems. InWorking Notes of the IJCAI Workshop on Adjustable Autonomy Systems, pages 16–35, 1999. 34

    1999