{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,3]],"date-time":"2026-05-03T02:25:15Z","timestamp":1777775115791,"version":"3.51.4"},"reference-count":54,"publisher":"American Association for the Advancement of Science (AAAS)","issue":"113","funder":[{"DOI":"10.13039\/501100000780","name":"European Commission","doi-asserted-by":"publisher","award":["101070617"],"award-info":[{"award-number":["101070617"]}],"id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002347","name":"Bundesministerium f\u00fcr Bildung und Forschung","doi-asserted-by":"publisher","award":["16KIS2012"],"award-info":[{"award-number":["16KIS2012"]}],"id":[{"id":"10.13039\/501100002347","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002661","name":"Fonds De La Recherche Scientifique - FNRS","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002661","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002661","name":"Fonds De La Recherche Scientifique - FNRS","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002661","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Helmholtz Information & Data Science Academy"}],"content-domain":{"domain":["www.science.org"],"crossmark-restriction":true},"short-container-title":["Sci. Robot."],"published-print":{"date-parts":[[2026,4,29]]},"abstract":"<jats:p>Robot swarms are composed of many, typically simple, robots that accomplish complex tasks through local communication and decentralized coordination. Traditionally, robot controllers are designed before a mission using programming code. This process requires substantial development effort and limits the flexibility of the swarm. We discuss how onboard foundation models (FMs) could revolutionize this process through two complementary approaches. The first approach uses FMs as swarm designers to synthesize robot controllers and perform high-level planning. The second approach uses FMs as swarm operators to facilitate robot-robot collaboration and human-swarm interaction.<\/jats:p>","DOI":"10.1126\/scirobotics.adz1543","type":"journal-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T18:01:01Z","timestamp":1777485661000},"update-policy":"https:\/\/doi.org\/10.34133\/aaas_crossmark","source":"Crossref","is-referenced-by-count":0,"title":["How foundation models will revolutionize robot swarms"],"prefix":"10.1126","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2974-9827","authenticated-orcid":true,"given":"Volker","family":"Strobel","sequence":"first","affiliation":[{"name":"IRIDIA, Universit\u00e9 Libre de Bruxelles, Brussels, Belgium."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3971-0507","authenticated-orcid":true,"given":"Marco","family":"Dorigo","sequence":"additional","affiliation":[{"name":"IRIDIA, Universit\u00e9 Libre de Bruxelles, Brussels, Belgium."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8949-9896","authenticated-orcid":true,"given":"Mario","family":"Fritz","sequence":"additional","affiliation":[{"name":"CISPA Helmholtz Center for Information Security, St. Ingbert, Germany."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"221","reference":[{"key":"e_1_3_1_2_2","doi-asserted-by":"crossref","unstructured":"H. Hamann Swarm Robotics: A Formal Approach (Springer 2018).","DOI":"10.1007\/978-3-319-74528-2"},{"key":"e_1_3_1_3_2","doi-asserted-by":"crossref","unstructured":"E. \u015eahin \u201cSwarm robotics: From sources of inspiration to domains of application\u201d in Proceedings of the 2004 International Conference on Swarm Robotics (SAB\u201904) (Springer 2004) pp. 10\u201320.","DOI":"10.1007\/978-3-540-30552-1_2"},{"key":"e_1_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1504\/IJMIC.2006.008645"},{"key":"e_1_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aar7650"},{"key":"e_1_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2023.1134841"},{"key":"e_1_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11721-014-0092-4"},{"key":"e_1_3_1_8_2","doi-asserted-by":"crossref","unstructured":"D. Garzon Ramos M. Birattari \u201cAutomatically designing robot swarms in environments populated by other robots: An experiment in robot shepherding\u201d in Proceedings of the IEEE International Conference on Robotics and Automation (ICRA 2024) (IEEE 2024) pp. 12240\u201312247.","DOI":"10.1109\/ICRA57147.2024.10611309"},{"key":"e_1_3_1_9_2","doi-asserted-by":"crossref","unstructured":"V. Trianni E. Tuci C. Ampatzis M. Dorigo \u201cEvolutionary swarm robotics: A theoretical and methodological itinerary from individual neuro-controllers to collective behaviours\u201d in The Horizons of Evolutionary Robotics (MIT Press 2014) vol. 153.","DOI":"10.7551\/mitpress\/8493.003.0008"},{"key":"e_1_3_1_10_2","first-page":"671","article-title":"Learning decentralized controllers for robot swarms with graph neural networks","volume":"100","author":"Tolstaya E.","year":"2020","unstructured":"E. Tolstaya, F. Gama, J. Paulos, G. Pappas, V. Kumar, A. Ribeiro, Learning decentralized controllers for robot swarms with graph neural networks. Proc. Mach. Learn. Res. 100, 671\u2013682 (2020).","journal-title":"Proc. Mach. Learn. Res."},{"key":"e_1_3_1_11_2","unstructured":"V. Strobel M. Dorigo M. Fritz \u201cLLM2Swarm: Robot swarms that responsively reason plan and collaborate through LLMs\u201d in NeurIPS 2024 Workshop on Open-World Agents (OWA2024) (Curran Associates Inc. 2024)."},{"key":"e_1_3_1_12_2","unstructured":"R. Bommasani D. A. Hudson E. Adeli R. Altman S. Arora S. von Arx M. S. Bernstein J. Bohg A. Bosselut E. Brunskill E. Brynjolfsson S. Buch D. Card R. Castellon N. Chatterji A. Chen K. Creel J. Q. Davis D. Demszky C. Donahue M. Doumbouya E. Durmus S. Ermon J. Etchemendy K. Ethayarajh L. Fei-Fei C. Finn T. Gale L. Gillespie K. Goel N. Goodman S. Grossman N. Guha T. Hashimoto P. Henderson J. Hewitt D. E. Ho J. Hong K. Hsu J. Huang T. Icard S. Jain D. Jurafsky P. Kalluri S. Karamcheti G. Keeling F. Khani O. Khattab P. W. Koh M. Krass R. Krishna R. Kuditipudi A. Kumar F. Ladhak M. Lee T. Lee J. Leskovec I. Levent X. L. Li X. Li T. Ma A. Malik C. D. Manning S. Mirchandani E. Mitchell Z. Munyikwa S. Nair A. Narayan D. Narayanan B. Newman A. Nie J. C. Niebles H. Nilforoshan J. Nyarko G. Ogut L. Orr I. Papadimitriou J. S. Park C. Piech E. Portelance C. Potts A. Raghunathan R. Reich H. Ren F. Rong Y. Roohani C. Ruiz J. Ryan C. R\u00e9 D. Sadigh S. Sagawa K. Santhanam A. Shih K. Srinivasan A. Tamkin R. Taori A. W. Thomas F. Tram\u00e8r R. E. Wang W. Wang B. Wu J. Wu Y. Wu S. M. Xie M. Yasunaga J. You M. Zaharia M. Zhang T. Zhang X. Zhang Y. Zhang L. Zheng K. Zhou P. Liang On the opportunities and risks of foundation models. arXiv:2108.07258 [cs.LG] (2021)."},{"key":"e_1_3_1_13_2","doi-asserted-by":"crossref","unstructured":"K. Greshake S. Abdelnabi S. Mishra C. Endres T. Holz M. Fritz \u201cNot what you\u2019ve signed up for: Compromising real-world LLM-integrated applications with indirect prompt injection\u201d in Proceedings of the 16th ACM Workshop on Artificial Intelligence and Security AISec \u201923 (ACM 2023) pp. 79\u201390.","DOI":"10.1145\/3605764.3623985"},{"key":"e_1_3_1_14_2","unstructured":"Y. Shavit S. Agarwal M. Brundage S. Adler C. O\u2019Keefe R. Campbell T. Lee P. Mishkin T. Eloundou A. Hickey K. Slama L. Ahmad P. McMillan A. Beutel A. Passos D. G. Robinson Practices for governing agentic AI systems (Technical Report OpenAI 2023); https:\/\/cdn.openai.com\/papers\/practices-for-governing-agentic-ai-systems.pdf."},{"key":"e_1_3_1_15_2","doi-asserted-by":"crossref","unstructured":"S. Abdelnabi A. Gomaa S. Sivaprasad L. Schonherr M. Fritz \u201cCooperation competition and maliciousness: LLM-stakeholders interactive negotiation\u201d in Proceedings of the 38th International Conference on Neural Information Processing Systems (NeurIPS 2024) (Curran Associates Inc. 2024) pp. 83548\u201383599.","DOI":"10.52202\/079017-2658"},{"key":"e_1_3_1_16_2","doi-asserted-by":"crossref","unstructured":"S. Vemprala R. Bonatti A. Bucker A. Kapoor ChatGPT for robotics: Design principles and model abilities (Tech. Rep. MSR-TR-2023-8 Microsoft 2023); https:\/\/microsoft.com\/en-us\/research\/publication\/chatgpt-for-robotics-design-principles-and-model-abilities\/.","DOI":"10.1109\/ACCESS.2024.3387941"},{"key":"e_1_3_1_17_2","doi-asserted-by":"crossref","unstructured":"Y. Chen J. Arkin Y. Zhang N. Roy C. Fan \u201cScalable multi-robot collaboration with large language models: Centralized or decentralized systems?\u201d in Proceedings of the IEEE International Conference on Robotics and Automation (ICRA 2024) (IEEE 2024) pp. 4311\u20134317.","DOI":"10.1109\/ICRA57147.2024.10610676"},{"key":"e_1_3_1_18_2","doi-asserted-by":"crossref","unstructured":"Z. Mandi S. Jain S. Song \u201cRoCo: Dialectic multi-robot collaboration with large language models\u201d in Proceedings of the IEEE International Conference on Robotics and Automation (ICRA 2024) (IEEE 2024) pp. 286\u2013299.","DOI":"10.1109\/ICRA57147.2024.10610855"},{"key":"e_1_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1038\/s44182-025-00065-w"},{"key":"e_1_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11370-024-00550-5"},{"key":"e_1_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-023-10133-5"},{"key":"e_1_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11721-008-0015-3"},{"key":"e_1_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3124466"},{"key":"e_1_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1017\/S0263574708004323"},{"key":"e_1_3_1_25_2","doi-asserted-by":"crossref","unstructured":"C. H. Song J. Wu C. Washington B. M. Sadler W.-L. Chao Y. Su \u201cLLM-Planner: Few-shot grounded planning for embodied agents with large language models\u201d in Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (IEEE 2023) pp. 2998\u20133009.","DOI":"10.1109\/ICCV51070.2023.00280"},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cogr.2023.07.004"},{"key":"e_1_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2011.10.005"},{"key":"e_1_3_1_28_2","doi-asserted-by":"crossref","unstructured":"H. Hajipour K. Hassler T. Holz L. Schonherr M. Fritz \u201cCodeLMSec benchmark: Systematically evaluating and finding security vulnerabilities in black-box code language models\u201d in Proceedings of the 2nd IEEE Conference on Secure and Trustworthy Machine Learning (SATML 2024) (IEEE 2024).","DOI":"10.1109\/SaTML59370.2024.00040"},{"key":"e_1_3_1_29_2","unstructured":"MITRE Corporation Common weakness enumeration (CWE); https:\/\/cwe.mitre.org\/."},{"key":"e_1_3_1_30_2","doi-asserted-by":"crossref","unstructured":"A. Paas E. B. J. Coffey G. Beltrame D. St-Onge \u201cTowards evaluating the impact of swarm robotic control strategy on operators\u2019 cognitive load\u201d in Proceedings of the 31st IEEE International Conference on Robot and Human Interactive Communication (RO-MAN 2022) (IEEE 2022) pp. 217\u2013223.","DOI":"10.1109\/RO-MAN53752.2022.9900763"},{"key":"e_1_3_1_31_2","unstructured":"K. Ji X. Hu X. Zhang J. Chen \u201cAn LLM-based framework for human-swarm teaming cognition in disaster search and rescue\u201d in NeurIPS 2025 Workshop on LLM Persona Modeling (PersonaLLM) (Curran Associates Inc. 2025)."},{"key":"e_1_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.5898\/JHRI.5.1.Brown"},{"key":"e_1_3_1_33_2","doi-asserted-by":"crossref","unstructured":"I. Gharbi J. Kuckling D. G. Ramos M. Birattari \u201cShow me what you want: Inverse reinforcement learning to automatically design robot swarms by demonstration\u201d in Proceedings of the IEEE International Conference on Robotics and Automation (ICRA 2023) (IEEE 2023) pp. 5063\u20135070.","DOI":"10.1109\/ICRA48891.2023.10160947"},{"key":"e_1_3_1_34_2","first-page":"49523","article-title":"Will we run out of data? Limits of LLM scaling based on human-generated data","volume":"235","author":"Villalobos P.","year":"2024","unstructured":"P. Villalobos, A. Ho, J. Sevilla, T. Besiroglu, L. Heim, M. Hobbhahn, Will we run out of data? Limits of LLM scaling based on human-generated data. Proc. Mach. Learn. Res. 235, 49523\u201349544 (2024).","journal-title":"Proc. Mach. Learn. Res."},{"key":"e_1_3_1_35_2","doi-asserted-by":"crossref","unstructured":"J. Wilson S. Hauert \u201cSearch space illumination of robot swarm parameters for trustworthy interaction\u201d in International Symposium on Distributed Autonomous Robotic Systems (DARS 2022) (Springer 2022) pp. 173\u2013186.","DOI":"10.1007\/978-3-031-51497-5_13"},{"key":"e_1_3_1_36_2","first-page":"20240140","article-title":"Examining the human-centred challenges of human\u2013swarm interaction","volume":"383","author":"Lyons J. B.","year":"2025","unstructured":"J. B. Lyons, A. Capiola, J. A. Adams, J. D. Mator, E. Cherry, K. Barrera, Examining the human-centred challenges of human\u2013swarm interaction. Philos. Trans. R. Soc. London Ser. A Math. Phys. Eng. Sci. 383, 20240140 (2025).","journal-title":"Philos. Trans. R. Soc. London Ser. A Math. Phys. Eng. Sci."},{"key":"e_1_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2018.00011"},{"key":"e_1_3_1_38_2","unstructured":"S. Maheshwari C. Su \u201cNVIDIA JetPack 6.2 brings super mode to NVIDIA Jetson Orin Nano and Jetson Orin NX modules\u201d (NVIDIA 2025); https:\/\/developer.nvidia.com\/blog\/nvidia-jetpack-6-2-brings-super-mode-to-nvidia-jetson-orin-nano-and-jetson-orin-nx-modules\/."},{"key":"e_1_3_1_39_2","unstructured":"D. Kahneman Thinking Fast and Slow (Farrar Straus and Giroux 2011)."},{"key":"e_1_3_1_40_2","doi-asserted-by":"crossref","unstructured":"J. Howard S. Ruder \u201cUniversal language model fine-tuning for text classification\u201d in Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (ACL 2018) (ACL 2018) pp. 328\u2013339.","DOI":"10.18653\/v1\/P18-1031"},{"key":"e_1_3_1_41_2","doi-asserted-by":"crossref","unstructured":"T. Dettmers M. Lewis Y. Belkada L. Zettlemoyer \u201cGPT3.int8(): 8-bit matrix multiplication for transformers at scale\u201d in Advances in Neural Information Processing Systems 35 (NeurIPS 2022) (Curran Associates Inc. 2022) pp. 30318\u201330332.","DOI":"10.52202\/068431-2198"},{"key":"e_1_3_1_42_2","unstructured":"J. Lin J. Tang H. Tang S. Yang G. Xiao S. Han \u201cAWQ: Activation-aware weight quantization for on-device LLM compression and acceleration\u201d in Proceedings of the 7th Annual Conference on Machine Learning and Systems (MLSys 2024) (MLSys 2024) pp. 87\u2013100."},{"key":"e_1_3_1_43_2","first-page":"32332","article-title":"KIVI: A tuning-free asymmetric 2bit quantization for KVCache","volume":"235","author":"Liu Z.","year":"2024","unstructured":"Z. Liu, J. Yuan, H. Jin, S. Zhong, Z. Xu, V. Braverman, B. Chen, X. Hu, KIVI: A tuning-free asymmetric 2bit quantization for KVCache. Proc. Mach. Learn. Res. 235, 32332\u201332344 (2024).","journal-title":"Proc. Mach. Learn. Res."},{"key":"e_1_3_1_44_2","unstructured":"E. Frantar D. Alistarh \u201cSparseGPT: Massive language models can be accurately pruned in one-shot\u201d in Proceedings of the 40th International Conference on Machine Learning (ICML 2023) (JMLR 2023) pp. 10323\u201310337."},{"key":"e_1_3_1_45_2","doi-asserted-by":"crossref","unstructured":"X. Ma G. Fang X. Wang \u201cLLM-Pruner: On the structural pruning of large language models\u201d in Advances in Neural Information Processing Systems 36 (NeurIPS 2023) (Curran Associates Inc. 2023) pp. 21702\u201321720.","DOI":"10.52202\/075280-0950"},{"key":"e_1_3_1_46_2","unstructured":"G. Hinton O. Vinyals J. Dean Distilling the knowledge in a neural network. arXiv:1503.02531 [stat.ML] (2015)."},{"key":"e_1_3_1_47_2","doi-asserted-by":"crossref","unstructured":"T. Dao D. Fu S. Ermon A. Rudra C. R\u00e9 \u201cFlashAttention: Fast and memory-efficient exact attention with IO-awareness\u201d in Advances in Neural Information Processing Systems 35 (NeurIPS 2022) (Curran Associates Inc. 2022) pp. 16344\u201316359.","DOI":"10.52202\/068431-1189"},{"key":"e_1_3_1_48_2","unstructured":"K. Saito A. Wachi K. Wataoka Y. Akimoto \u201cVerbosity bias in preference labeling by large language models\u201d in NeurIPS 2023 Workshop on Instruction Tuning and Instruction Following (Curran Associates Inc. 2023)."},{"key":"e_1_3_1_49_2","unstructured":"P. Lewis E. Perez A. Piktus F. Petroni V. Karpukhin N. Goyal H. K\u00fcttler M. Lewis W.-t. Yih T. Rockt\u00e4schel S. Riedel D. Kiela \u201cRetrieval-augmented generation for knowledge-intensive NLP tasks\u201d in Proceedings of the 34th International Conference on Neural Information Processing Systems (NIPS 2020) (Curran Associates Inc. 2020)."},{"key":"e_1_3_1_50_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11721-012-0075-2"},{"key":"e_1_3_1_51_2","doi-asserted-by":"publisher","DOI":"10.1038\/s44287-024-00034-9"},{"key":"e_1_3_1_52_2","doi-asserted-by":"publisher","DOI":"10.1080\/14746700.2025.2472118"},{"key":"e_1_3_1_53_2","first-page":"20240142","article-title":"On the ethical governance of swarm robotic systems in the real world","volume":"383","author":"Winfield A. F.","year":"2025","unstructured":"A. F. Winfield, M. Swana, J. Ives, S. Hauert, On the ethical governance of swarm robotic systems in the real world. Philos. Trans. R. Soc. London Ser. A 383, 20240142 (2025).","journal-title":"Philos. Trans. R. Soc. London Ser. A"},{"key":"e_1_3_1_54_2","doi-asserted-by":"publisher","DOI":"10.1145\/3571730"},{"key":"e_1_3_1_55_2","unstructured":"I. Sheth J. Wehner S. Abdelnabi R. Binkyte M. Fritz \u201cSafety is essential for responsible open-ended systems\u201d in ICLR Workshop on Scaling Self-Improving Foundation Models without Human Supervision (ICLR 2025)."}],"container-title":["Science Robotics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.science.org\/doi\/pdf\/10.1126\/scirobotics.adz1543","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T18:01:28Z","timestamp":1777485688000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.science.org\/doi\/10.1126\/scirobotics.adz1543"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,29]]},"references-count":54,"journal-issue":{"issue":"113","published-print":{"date-parts":[[2026,4,29]]}},"alternative-id":["10.1126\/scirobotics.adz1543"],"URL":"https:\/\/doi.org\/10.1126\/scirobotics.adz1543","relation":{},"ISSN":["2470-9476"],"issn-type":[{"value":"2470-9476","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,29]]},"assertion":[{"value":"2025-05-25","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-04-01","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-04-29","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"eadz1543"}}