pith. sign in

arxiv: 2604.04753 · v2 · pith:D5IWQOCJnew · submitted 2026-04-06 · 📡 eess.SY · cs.SY

Toward Self-Organizing Production Logistics: A Multi-Agent Approach

Jan-Felix Klein , Yongkuk Jeong , Erik Flores-Garc\'ia , Magnus Wiktorsson This is my paper

Pith reviewed 2026-05-22 11:14 UTC · model grok-4.3

classification 📡 eess.SY cs.SY
keywords self-organizing production logisticsmulti-agent systemsautonomous logistics resourcesdistributed decision-makingdigital twinsevent-driven coordinationproduction disturbances
0
0 comments X

The pith

Self-organizing production logistics can emerge from a multi-agent architecture that mixes embodied and non-embodied agents with event-driven coordination and digital twins.

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

Production logistics faces growing variability, interdependencies, and disturbances that overwhelm traditional centralized control, especially in circular systems. The paper derives system-level objectives and design requirements from drivers such as autonomous resources and distributed AI decision-making. It then proposes an initial multi-agent architecture that incorporates embodied and non-embodied agents, semantic knowledge structures, and digital twins to enable self-organization. A three-phase demonstration roadmap is outlined, beginning with laboratory tests of disturbance handling in order-driven kitting scenarios.

Core claim

The paper establishes a conceptual foundation for Self-Organizing Production Logistics through a multi-agent architecture that integrates autonomous logistics resources, distributed decision-making, event-driven coordination, semantic knowledge, and digital twins to manage dynamic conditions without relying on central planning.

What carries the argument

The initial multi-agent architecture for SOPL, which combines embodied and non-embodied agents with event-driven coordination, semantic knowledge structures, and digital twins to support distributed adaptation.

If this is right

  • Production systems gain the ability to respond to disturbances through local agent interactions rather than top-down rescheduling.
  • Human roles shift toward supervisory coordination while routine logistics decisions become handled by the agent network.
  • Circular production setups become more practical because agents can adapt to changing material loops and interdependencies in real time.

Where Pith is reading between the lines

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

  • The same architecture could apply to broader supply-chain networks where physical distances make central control inefficient.
  • Scalability questions remain open, such as how agent communication overhead grows when the system expands beyond the initial laboratory scale.
  • Integration with legacy factory software would likely require new interfaces for semantic data exchange between agents and existing planning tools.

Load-bearing premise

Autonomous logistics resources and distributed AI-based decision-making will reliably produce self-organization and effective disturbance handling without central oversight or extensive human intervention.

What would settle it

Run the Phase I laboratory demonstrator on an order-driven kitting and supply scenario, introduce repeated operational disturbances, and measure whether the multi-agent system maintains performance through self-coordination alone without added central rules or human overrides.

Figures

Figures reproduced from arXiv: 2604.04753 by Erik Flores-Garc\'ia, Jan-Felix Klein, Magnus Wiktorsson, Yongkuk Jeong.

Figure 1
Figure 1. Figure 1: Methodology linking emerging drivers, the system vision, and a [PITH_FULL_IMAGE:figures/full_fig_p002_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Recent industrial pilot deployments of humanoid robots performing pro [PITH_FULL_IMAGE:figures/full_fig_p004_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Conceptual vision of an SOPL system in the circular factory, combining [PITH_FULL_IMAGE:figures/full_fig_p007_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: A three-phase development roadmap toward self-organizing production [PITH_FULL_IMAGE:figures/full_fig_p009_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Phase 1 experimental setup in the IPU Lab at KTH, where heterogeneous [PITH_FULL_IMAGE:figures/full_fig_p011_5.png] view at source ↗
read the original abstract

Production logistics (PL) is increasingly exposed to variability, dynamic interdependencies, and operational disturbances that challenge conventional centralized planning and control. These characteristics are particularly pronounced in circular production systems, but are increasingly relevant across PL more generally. This paper addresses this challenge through the concept of Self-Organizing Production Logistics (SOPL) using the Design Science Research Methodology (DSRM) as a structuring framework. The paper identifies key technological and systemic drivers motivating SOPL, including autonomous logistics resources, distributed AI-based decision-making, and increasing operational uncertainty in circular production. Based on these drivers, system-level objectives and design requirements for SOPL are derived. Building on these requirements, an initial multi-agent architecture is proposed that combines embodied and non-embodied agents, event-driven coordination, semantic knowledge structures, and digital twins. In addition, a three-phase demonstration roadmap is presented, ranging from an initial laboratory demonstrator toward increasingly distributed and adaptive SOPL systems. The Phase I demonstrator serves as an experimental setup for investigating disturbance handling, human involvement, and supervisory coordination in an order-driven kitting and supply scenario. Overall, the paper contributes a conceptual foundation for the design, implementation, and experimental evaluation of SOPL systems.

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 claims to address challenges in production logistics due to variability, dynamic interdependencies, and disturbances—especially in circular systems—by introducing the concept of Self-Organizing Production Logistics (SOPL). Using Design Science Research Methodology (DSRM) as a framework, it identifies drivers such as autonomous logistics resources, distributed AI-based decision-making, and increasing operational uncertainty; derives system-level objectives and design requirements; proposes an initial multi-agent architecture combining embodied and non-embodied agents, event-driven coordination, semantic knowledge structures, and digital twins; and outlines a three-phase demonstration roadmap beginning with a laboratory demonstrator for order-driven kitting and supply scenarios focused on disturbance handling, human involvement, and supervisory coordination.

Significance. If the proposed architecture can be shown through the outlined roadmap to enable emergent self-organization and reliable disturbance handling, this work would provide a valuable conceptual foundation for decentralized production logistics systems. The structured application of DSRM and the integration of digital twins with multi-agent coordination address a timely need in resilient and circular manufacturing, potentially guiding future implementations that reduce dependence on centralized planning.

major comments (2)
  1. [Requirements Derivation] The derivation of system-level objectives and design requirements from the identified drivers (autonomous resources, distributed AI, and uncertainty in circular production) is presented at a conceptual level without an explicit mapping, traceability table, or justification showing how each requirement addresses specific drivers or mitigates interdependencies. This makes it difficult to assess whether the requirements are complete and directly support the central SOPL claims.
  2. [Multi-Agent Architecture Proposal] The manuscript asserts that the proposed multi-agent architecture (embodied/non-embodied agents, event-driven coordination, semantic structures, and digital twins) satisfies the design requirements for self-organization and disturbance handling without central oversight, yet supplies only a high-level description with no interaction rules, decision protocols, formal analysis, or preliminary results demonstrating emergent behavior or reliable performance. This leaves the core claim unsubstantiated within the current scope.
minor comments (2)
  1. [Demonstration Roadmap] The three-phase demonstration roadmap is outlined but would benefit from additional detail on evaluation metrics for self-organization and disturbance handling in the Phase I laboratory demonstrator to strengthen the experimental plan.
  2. [Architecture Description] Terminology such as 'embodied' versus 'non-embodied' agents and 'semantic knowledge structures' is introduced without explicit definitions or examples in the main text, which could improve accessibility for readers outside the immediate subfield.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive comments and for recognizing the potential value of this conceptual contribution to decentralized production logistics. We address each major comment below and outline the revisions we will make to strengthen the manuscript.

read point-by-point responses

  1. Referee: [Requirements Derivation] The derivation of system-level objectives and design requirements from the identified drivers (autonomous resources, distributed AI, and uncertainty in circular production) is presented at a conceptual level without an explicit mapping, traceability table, or justification showing how each requirement addresses specific drivers or mitigates interdependencies. This makes it difficult to assess whether the requirements are complete and directly support the central SOPL claims.

    Authors: We agree that the current conceptual presentation would benefit from greater traceability. In the revised version we will insert a dedicated traceability table that explicitly maps each driver to the derived system-level objectives and design requirements, with short justifications explaining how each requirement addresses interdependencies and supports the SOPL claims. This addition will make the derivation more transparent and easier to evaluate for completeness. revision: yes

  2. Referee: [Multi-Agent Architecture Proposal] The manuscript asserts that the proposed multi-agent architecture (embodied/non-embodied agents, event-driven coordination, semantic structures, and digital twins) satisfies the design requirements for self-organization and disturbance handling without central oversight, yet supplies only a high-level description with no interaction rules, decision protocols, formal analysis, or preliminary results demonstrating emergent behavior or reliable performance. This leaves the core claim unsubstantiated within the current scope.

    Authors: The manuscript is deliberately scoped as a conceptual foundation derived via DSRM; detailed interaction rules, decision protocols, and formal analysis are planned for subsequent phases of the three-phase roadmap. We will revise the text to clarify that the architecture description is intentionally high-level at this stage and that the Phase I laboratory demonstrator will serve to investigate emergent self-organization, disturbance handling, human involvement, and the role of supervisory coordination. Where space allows, we will also add high-level pseudocode or rule outlines for the key coordination mechanisms to make the proposal more concrete. revision: partial

Circularity Check

0 steps flagged

No circularity detected in conceptual derivation from drivers to requirements to architecture

full rationale

The paper follows the Design Science Research Methodology by first identifying drivers such as autonomous logistics resources, distributed AI-based decision-making, and operational uncertainty in circular production. It then derives system-level objectives and design requirements directly from these drivers. Building on the requirements, it proposes an initial multi-agent architecture combining embodied and non-embodied agents, event-driven coordination, semantic knowledge structures, and digital twins, along with a three-phase demonstration roadmap. This chain contains no equations, fitted parameters, self-definitional constructs, or load-bearing self-citations that would make any claimed result equivalent to its inputs by construction. The work is a forward-looking conceptual framework without predictive claims that reduce to prior fits or renamings, rendering the derivation self-contained.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 1 invented entities

The central claim rests on domain assumptions about the feasibility of autonomous resources and distributed AI rather than new mathematical axioms or fitted parameters. No free parameters or invented physical entities are introduced.

axioms (1)
  • domain assumption Autonomous logistics resources and distributed AI-based decision-making are viable and will enable effective self-organization in production environments
    Invoked to motivate SOPL and derive design requirements from the listed technological drivers.
invented entities (1)
  • Self-Organizing Production Logistics (SOPL) no independent evidence
    purpose: A new organizing concept for handling variability in circular production logistics
    Introduced as the target framework without independent empirical evidence or falsifiable predictions in the provided abstract.

pith-pipeline@v0.9.0 · 5758 in / 1302 out tokens · 38037 ms · 2026-05-22T11:14:27.774387+00:00 · methodology

Review history (2 revisions) →

discussion (0)

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

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

What do these tags mean?
matches
The paper's claim is directly supported by a theorem in the formal canon.
supports
The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends
The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses
The paper appears to rely on the theorem as machinery.
contradicts
The paper's claim conflicts with a theorem or certificate in the canon.
unclear
Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Reference graph

Works this paper leans on

33 extracted references · 33 canonical work pages · 1 internal anchor

  1. [1]

    https://doi.org/10.1109/iros60139.2025.11247690

    AgiBot World Colosseo: A Large-Scale Manipulation Platform for Scalable and Intelligent Embodied Systems. In: 2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). pp. 3549–3556. IEEE (2025). https://doi. org/10.1109/IROS60139.2025.11247088

    work page doi:10.1109/iros60139.2025.11247088 2025

  2. [2]

    https: //www.agilityrobotics.com/content/digit-moves-over-100k-totes (2025), accessed: 2026-03-15

    Agility Robotics: Digit moves over 100,000 totes in commercial deployment. https: //www.agilityrobotics.com/content/digit-moves-over-100k-totes (2025), accessed: 2026-03-15

    work page 2025

  3. [3]

    https: //www.bmwgroup.com/en/news/general/2026/humanoid-robot-in-leipzig.html (2026), accessed: 2026-03-15

    BMW Group: First humanoid robot introduced in plant leipzig. https: //www.bmwgroup.com/en/news/general/2026/humanoid-robot-in-leipzig.html (2026), accessed: 2026-03-15

    work page 2026

  4. [4]

    (ed.): Self-organization in biological systems

    Camazine, S. (ed.): Self-organization in biological systems. Princeton studies in complexity, Princeton University Press, Princeton, NJ, 2nd print., and 1st paper- back print edn. (2003)

    work page 2003

  5. [5]

    Journal of Manufacturing Systems 59, 386–397 (2021)

    Diaz C., J.L., Ocampo-Martinez, C.: Non-centralised control strategies for energy- efficient and flexible manufacturing systems. Journal of Manufacturing Systems 59, 386–397 (2021). https://doi.org/10.1016/j.jmsy.2021.02.004 14 J.-F. Klein et al

    work page doi:10.1016/j.jmsy.2021.02.004 2021

  6. [6]

    https://environment.ec

    European Commission: Circular economy – environment. https://environment.ec. europa.eu/strategy/circular-economy_en (2025), accessed 2026-02-10 and Circular Economy Act due for adoption in 2026

    work page 2025

  7. [7]

    https:// www.figure.ai/news/production-at-bmw (2025), accessed: 2026-03-14

    Figure AI: F.02 contributed to the production of 30000 cars at BMW. https:// www.figure.ai/news/production-at-bmw (2025), accessed: 2026-03-14

    work page 2025

  8. [8]

    at - Au- tomatisierungstechnik72(9), 861–874 (2024)

    Fleischer, J., Zanger, F., Schulze, V., Neumann, G., Stricker, N., Furmans, K., Pfrommer, J., Lanza, G., Hansjosten, M., Fischmann, P., Dvorak, J., Klein, J.F., Rauscher, F., Ebner, A., May, M.C., Gönnheimer, P.: Self-learning and au- tonomously adapting manufacturing equipment for the circular factory. at - Au- tomatisierungstechnik72(9), 861–874 (2024)....

    work page doi:10.1515/auto-2024- 2024

  9. [9]

    PhD, University of Twente, Enschede, The Netherlands (2023)

    Gerrits, B.: Self-Organizing Logistics : Towards a unifying framework for auto- mated transport systems. PhD, University of Twente, Enschede, The Netherlands (2023). https://doi.org/10.3990/1.9789036555555

    work page doi:10.3990/1.9789036555555 2023

  10. [10]

    International Transactions in Opera- tional Research31(3), 1309–1374 (2024)

    Gerrits, B., Van Heeswijk, W., Mes, M.: Towards self-organizing logistics in trans- portation: a literature review and typology. International Transactions in Opera- tional Research31(3), 1309–1374 (2024). https://doi.org/10.1111/itor.13408

    work page doi:10.1111/itor.13408 2024

  11. [11]

    at - Automatisierung- stechnik72(9), 875–883 (2024)

    Hofmann, C., Staab, S., Selzer, M., Neumann, G., Furmans, K., Heizmann, M., Beyerer, J., Lanza, G., Pfrommer, J., Düser, T., Klein, J.F.: The role of an ontology-based knowledge backbone in a circular factory. at - Automatisierung- stechnik72(9), 875–883 (2024). https://doi.org/10.1515/auto-2024-0006, https: //www.degruyter.com/document/doi/10.1515/auto-2...

    work page doi:10.1515/auto-2024-0006 2024

  12. [12]

    https://thehumanoid.ai/humanoid-and-siemens- completed-a-proof-of-concept-to-test-humanoidrobots-in-industrial-logistics/ (2026), accessed: 2026-03-14

    Humanoid: Humanoid and siemens completed a proof of concept to test humanoid robots in industrial logistics. https://thehumanoid.ai/humanoid-and-siemens- completed-a-proof-of-concept-to-test-humanoidrobots-in-industrial-logistics/ (2026), accessed: 2026-03-14

    work page 2026

  13. [13]

    International Federation of Robotics: World robotics report 2025: Service robots (2025), https://ifr.org/worldrobotics, accessed: 2026-01-28

    work page 2025

  14. [14]

    American Institute of Physics Conference Series, vol

    Ismayyir, D.K., Dawood, L.M., AL-Khafaji, M.M.H.: Modelling and control archi- tecturesofproductionsystems:Literaturereview.In:AmericanInstituteofPhysics Conference Series. American Institute of Physics Conference Series, vol. 3079, p. 060022. AIP (2024). https://doi.org/10.1063/5.0202238

    work page doi:10.1063/5.0202238 2024

  15. [15]

    https://bostondynamics.com/blog/ getting-real-with-humanoids/ (2025), accessed: 2026-03-15

    Jackowski, Z.: Getting real with humanoids. https://bostondynamics.com/blog/ getting-real-with-humanoids/ (2025), accessed: 2026-03-15

    work page 2025

  16. [16]

    Procedia CIRP120, 368–373 (2023)

    Klein, J.F., Furmans, K.: Digital twin architecture and sim-to-real gap analysis of a material transfer system in a remanufacturing environment. Procedia CIRP120, 368–373 (2023). https://doi.org/10.1016/j.procir.2023.09.004

    work page doi:10.1016/j.procir.2023.09.004 2023

  17. [17]

    Logistics Journal: Proceedings (21) (2025)

    Klein, J.F., Wolf, R., Ernst, A., Shi, Y., Schumacher, P., Thapa, R.B., Rayyes, R., Furmans, K.: A Knowledge-Based Intralogistic System for a Circular Factory. Logistics Journal: Proceedings (21) (2025). https://doi.org/10.2195/LJ_PROC_ KLEIN_202510_01

    work page doi:10.2195/lj_proc_ 2025

  18. [18]

    at - Automatisierung- stechnik70(6), 504–516 (2022)

    Lanza, G., Asfour, T., Beyerer, J., Deml, B., Fleischer, J., Heizmann, M., Fur- mans, K., Hofmann, C., Cebulla, A., Dreher, C., Kaiser, J.P., Klein, J.F., Leven, F., Mangold, S., Mitschke, N., Stricker, N., Pfrommer, J., Wu, C., Wurster, M., Zaremski, M.: Agiles Produktionssystem mittels lernender Roboter bei ungewissen Produktzuständen am Beispiel der An...

    work page doi:10.1515/auto-2021-0158 2022

  19. [19]

    at - Automa- tisierungstechnik72(9), 774–788 (2024)

    Lanza, G., Deml, B., Matthiesen, S., Martin, M., Brützel, O., Hörsting, R.: The vision of the circular factory for the perpetual innovative product. at - Automa- tisierungstechnik72(9), 774–788 (2024). https://doi.org/10.1515/auto-2024-0012 Toward Self-Organizing Production Logistics 15

    work page doi:10.1515/auto-2024-0012 2024

  20. [20]

    Vicinagearth1(1), 9 (2024)

    Li, X., Wang, S., Zeng, S., Wu, Y., Yang, Y.: A survey on LLM-based multi-agent systems: workflow, infrastructure, and challenges. Vicinagearth1(1), 9 (2024). https://doi.org/10.1007/s44336-024-00009-2

    work page doi:10.1007/s44336-024-00009-2 2024

  21. [21]

    LogisticsIQ: AGV-AMR Market (2025), https://www.thelogisticsiq.com/research/ automated-guided-vehicles-agv-market/, accessed: 2026-01-28

    work page 2025

  22. [22]

    European Jour- nal of Operational Research181(1), 59–75 (2007)

    Mes,M.,VanDerHeijden,M.,VanHarten,A.:Comparisonofagent-basedschedul- ing to look-ahead heuristics for real-time transportation problems. European Jour- nal of Operational Research181(1), 59–75 (2007). https://doi.org/10.1016/j.ejor. 2006.02.051

    work page doi:10.1016/j.ejor 2007

  23. [23]

    IEEE Trans

    Pan, S., Luo, L., Wang, Y., Chen, C., Wang, J., Wu, X.: Unifying Large Language Models and Knowledge Graphs: A Roadmap. IEEE Transactions on Knowledge and Data Engineering36(7), 3580–3599 (2024). https://doi.org/10.1109/TKDE. 2024.3352100

    work page doi:10.1109/tkde 2024

  24. [24]

    CRC Press, 1 edn

    Pariès, J., Wreathall, J.: Resilience Engineering in Practice: A Guidebook. CRC Press, 1 edn. (May 2017). https://doi.org/10.1201/9781317065265

    work page doi:10.1201/9781317065265 2017

  25. [25]

    at - Automatisierungstechnik70(6), 534–541 (2022)

    Pfrommer, J., Klein, J.F., Wurster, M., Rapp, S., Grauberger, P., Lanza, G., Al- bers, A., Matthiesen, S., Beyerer, J.: An ontology for remanufacturing systems. at - Automatisierungstechnik70(6), 534–541 (2022). https://doi.org/10.1515/auto- 2021-0156

    work page doi:10.1515/auto- 2022

  26. [26]

    The International Journal of Advanced Manufacturing Technology84(1-4), 147– 164 (2016)

    Qu, T., Lei, S.P., Wang, Z.Z., Nie, D.X., Chen, X., Huang, G.Q.: IoT-based real- timeproductionlogisticssynchronizationsystemundersmartcloudmanufacturing. The International Journal of Advanced Manufacturing Technology84(1-4), 147– 164 (2016). https://doi.org/10.1007/s00170-015-7220-1

    work page doi:10.1007/s00170-015-7220-1 2016

  27. [27]

    Scientific Reports15(1), 13755 (2025)

    Raza, M., Jahangir, Z., Riaz, M.B., Saeed, M.J., Sattar, M.A.: Industrial appli- cations of large language models. Scientific Reports15(1), 13755 (2025). https: //doi.org/10.1038/s41598-025-98483-1

    work page doi:10.1038/s41598-025-98483-1 2025

  28. [28]

    Ad- vances in Manufacturing5(4), 344–358 (2017)

    Strandhagen, J.W., Alfnes, E., Strandhagen, J.O., Vallandingham, L.R.: The fit of Industry 4.0 applications in manufacturing logistics: a multiple case study. Ad- vances in Manufacturing5(4), 344–358 (2017). https://doi.org/10.1007/s40436- 017-0200-y

    work page doi:10.1007/s40436- 2017

  29. [29]

    Multi-Agent Collaboration Mechanisms: A Survey of LLMs

    Tran, K.T., Dao, D., Nguyen, M.D., Pham, Q.V., O’Sullivan, B., Nguyen, H.D.: Multi-Agent Collaboration Mechanisms: A Survey of LLMs (2025). https://doi. org/10.48550/ARXIV.2501.06322

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.48550/arxiv.2501.06322 2025

  30. [30]

    UBTECH Robotics: Unleashing swarm intelligence: UBTECH pioneers the world’s first multi-humanoid robot collaborative training in multi-task, multi-scenario set- tings at ZEEKR. https://www.prnewswire.com/news-releases/unleashing-swarm- intelligence-ubtech-pioneers-the-worlds-first-multi-humanoid-robot-collaborative- training-in-multi-task-multi-scenario-s...

    work page 2025

  31. [31]

    Sustainable Production and Consumption33, 1043–1058 (2022)

    Viles, E., Kalemkerian, F., Garza-Reyes, J.A., Antony, J., Santos, J.: Theoriz- ing the Principles of Sustainable Production in the context of Circular Economy and Industry 4.0. Sustainable Production and Consumption33, 1043–1058 (2022). https://doi.org/10.1016/j.spc.2022.08.024

    work page doi:10.1016/j.spc.2022.08.024 2022

  32. [32]

    In: Hülsmann, M., Windt, K

    Windt, K., Hülsmann, M.: Changing Paradigms in Logistics — Understanding the Shift from Conventional Control to Autonomous Cooperation and Control. In: Hülsmann, M., Windt, K. (eds.) Understanding Autonomous Cooperation and Control in Logistics, pp. 1–16. Springer Berlin Heidelberg, Berlin, Heidelberg (2007). https://doi.org/10.1007/978-3-540-47450-0_1

    work page doi:10.1007/978-3-540-47450-0_1 2007

  33. [33]

    Magma: A founda- tion model for multimodal ai agents

    Yang, J., Tan, R., Wu, Q., Zheng, R., Peng, B., Liang, Y., Gu, Y., Cai, M., Ye, S., Jang, J., Deng, Y., Liden, L., Gao, J.: Magma: A Foundation Model for Multimodal AI Agents (2025). https://doi.org/10.48550/ARXIV.2502.13130

    work page doi:10.48550/arxiv.2502.13130 2025