{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T12:01:35Z","timestamp":1777982495171,"version":"3.51.4"},"reference-count":56,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T00:00:00Z","timestamp":1775865600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T00:00:00Z","timestamp":1775865600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Thales Land and Air Systems, BL IAS"},{"name":"Universit\u00e9 Grenoble Alpe"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Auton Agent Multi-Agent Syst"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1007\/s10458-026-09740-0","type":"journal-article","created":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T09:25:16Z","timestamp":1775899516000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Assisting multi-agent systems design with $$\\mathcal {M}OISE^+$$ and MARL: The MAMAD method"],"prefix":"10.1007","volume":"40","author":[{"given":"Julien","family":"Soul\u00e9","sequence":"first","affiliation":[]},{"given":"Jean-Paul","family":"Jamont","sequence":"additional","affiliation":[]},{"given":"Michel","family":"Occello","sequence":"additional","affiliation":[]},{"given":"Louis-Marie","family":"Traonouez","sequence":"additional","affiliation":[]},{"given":"Paul","family":"Th\u00e9ron","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,4,11]]},"reference":[{"key":"9740_CR1","doi-asserted-by":"crossref","unstructured":"Wooldridge, M., Jennings, N.R., & Kinny, D. (1998). The gaia methodology for agent-oriented analysis and design. In Autonomous Agents and Multi-Agent Systems, (pp. 285\u2013312).","DOI":"10.1023\/A:1010071910869"},{"key":"9740_CR2","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1007\/3-540-39173-8_12","volume-title":"Engineering Societies in the Agents World III","author":"C Bernon","year":"2003","unstructured":"Bernon, C., Gleizes, M.-P., Peyruqueou, S., & Picard, G. (2003). Adelfe: A methodology for adaptive multi-agent systems engineering. In P. Petta, R. Tolksdorf, & F. Zambonelli (Eds.), Engineering Societies in the Agents World III (pp. 156\u2013169). Berlin, Heidelberg: Springer."},{"key":"9740_CR3","doi-asserted-by":"publisher","unstructured":"Jamont, J.-P., & Occello, M. (2007). Designing embedded collective systems: The diamond multiagent method. In 19th IEEE International Conference on Tools with Artificial Intelligence(ICTAI 2007), (vol. 2, pp. 91\u201394). https:\/\/doi.org\/10.1109\/ICTAI.2007.34.","DOI":"10.1109\/ICTAI.2007.34."},{"key":"9740_CR4","doi-asserted-by":"publisher","first-page":"394","DOI":"10.1007\/3-540-45023-8_38","volume-title":"Multi-Agent Systems and Applications III","author":"J Pav\u00f3n","year":"2003","unstructured":"Pav\u00f3n, J., & G\u00f3mez-Sanz, J. (2003). Agent oriented software engineering with ingenias. In V. Ma\u0159\u00edk, M. P\u011bchou\u010dek, & J. M\u00fcller (Eds.), Multi-Agent Systems and Applications III (pp. 394\u2013403). Berlin, Heidelberg: Springer."},{"key":"9740_CR5","first-page":"1","volume-title":"Multi-Agent System Engineering","author":"NR Jennings","year":"1999","unstructured":"Jennings, N. R. (1999). Agent-oriented software engineering. In F. J. Garijo & M. Boman (Eds.), Multi-Agent System Engineering (pp. 1\u20137). Berlin, Heidelberg: Springer."},{"key":"9740_CR6","first-page":"1","volume-title":"Engineering Multi-Agent Systems","author":"KV Hindriks","year":"2014","unstructured":"Hindriks, K. V. (2014). The shaping of the agent-oriented mindset. In F. Dalpiaz, J. Dix, & M. B. Riemsdijk (Eds.), Engineering Multi-Agent Systems (pp. 1\u201314). Cham: Springer."},{"issue":"1","key":"9740_CR7","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1504\/IJAOSE.2015.078435","volume":"5","author":"J-P Jamont","year":"2015","unstructured":"Jamont, J.-P., & Occello, M. (2015). Meeting the challenges of decentralised embedded applications using multi-agent systems. International Journal of Agent-Oriented Software Engineering, 5(1), 22\u201368. https:\/\/doi.org\/10.1504\/IJAOSE.2015.078435","journal-title":"International Journal of Agent-Oriented Software Engineering"},{"issue":"2","key":"9740_CR8","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1007\/s10458-007-9023-8","volume":"16","author":"M Sims","year":"2008","unstructured":"Sims, M., Corkill, D., & Lesser, V. (2008). Automated organization design for multi-agent systems. Autonomous Agents and Multi-Agent Systems, 16(2), 151\u2013185. https:\/\/doi.org\/10.1007\/s10458-007-9023-8","journal-title":"Autonomous Agents and Multi-Agent Systems"},{"key":"9740_CR9","unstructured":"Harper, J. (2024). Autogenesisagent: Self-generating multi-agent systems for complex tasks. arXiv preprint arXiv:2404.17017."},{"key":"9740_CR10","unstructured":"Ha, D., & Schmidhuber, J. (2018). World models. arxiv:1803.10122 ."},{"key":"9740_CR11","doi-asserted-by":"publisher","unstructured":"Zhang, K., Yang, Z., & Ba\u015far, T. (2021). In K. G. Vamvoudakis, Y. Wan, F. L. Lewis, & D. Cansever, (eds.), Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms, (pp. 321\u2013384). Springer, Cham. https:\/\/doi.org\/10.1007\/978-3-030-60990-0_12.","DOI":"10.1007\/978-3-030-60990-0_12."},{"key":"9740_CR12","unstructured":"Papoudakis, G., Christianos, F., Sch\u00e4fer, L., & Albrecht, S. (2021). Benchmarking multi-agent deep reinforcement learning algorithms in cooperative tasks. In J. Vanschoren, & S. Yeung, (eds.), Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks, (vol. 1)."},{"issue":"9","key":"9740_CR13","doi-asserted-by":"publisher","first-page":"3826","DOI":"10.1109\/TCYB.2020.2977374","volume":"50","author":"TT Nguyen","year":"2020","unstructured":"Nguyen, T. T., Nguyen, N. D., & Nahavandi, S. (2020). Deep reinforcement learning for multiagent systems: A review of challenges, solutions, and applications. IEEE Transactions on Cybernetics, 50(9), 3826\u20133839. https:\/\/doi.org\/10.1109\/TCYB.2020.2977374","journal-title":"IEEE Transactions on Cybernetics"},{"issue":"05","key":"9740_CR14","doi-asserted-by":"publisher","first-page":"7047","DOI":"10.1609\/aaai.v34i05.6190","volume":"34","author":"N Anastassacos","year":"2020","unstructured":"Anastassacos, N., Hailes, S., & Musolesi, M. (2020). Partner selection for the emergence of cooperation in multi-agent systems using reinforcement learning. Proceedings of the AAAI Conference on Artificial Intelligence, 34(05), 7047\u20137054. https:\/\/doi.org\/10.1609\/aaai.v34i05.6190","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"9740_CR15","doi-asserted-by":"crossref","unstructured":"Soule, J., Jamont, J.-P., Occello, M., Traonouez, L.-M., & Th\u00e9ron, P. (2025). An organizationally-oriented approach to enhancing explainability and control in multi-agent reinforcement learning. In Proceedings of the 24th International Conference on Autonomous Agents and Multiagent Systems.","DOI":"10.65109\/OHJD5218"},{"key":"9740_CR16","doi-asserted-by":"publisher","unstructured":"H\u00fcbner, J.F., Sichman, J.S., & Boissier, O. (2002). A model for the structural, functional, and deontic specification of organizations in multiagent systems. In G. Bittencourt, & G.L. Ramalho, (eds.), Advances in Artificial Intelligence, 16th Brazilian Symposium on Artificial Intelligence, SBIA 2002, Porto de Galinhas\/Recife, Brazil, November 11\u201314, 2002, Proceedings. Lecture Notes in Computer Science, (vol. 2507, pp. 118\u2013128). Springer, Online. https:\/\/doi.org\/10.1007\/3-540-36127-8_12.","DOI":"10.1007\/3-540-36127-8_12."},{"key":"9740_CR17","unstructured":"Smith, J., & Doe, J. (2024). Automated design of agentic systems. arXiv preprint arXiv:2408.08435."},{"key":"9740_CR18","unstructured":"Crawford, N., Duffy, E.B., Evazzade, I., Foehr, T., Robbins, G., Saha, D.K., Varma, J., & Ziolkowski, M. (2024). BMW Agents - A Framework For Task Automation Through Multi-Agent Collaboration. arxiv:2406.20041."},{"key":"9740_CR19","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1007\/978-3-031-50670-3_9","volume-title":"Decision and Game Theory for Security","author":"K Hammar","year":"2023","unstructured":"Hammar, K., & Stadler, R. (2023). Scalable learning of intrusion response through recursive decomposition. In J. Fu, T. Kroupa, & Y. Hayel (Eds.), Decision and Game Theory for Security (pp. 172\u2013192). Cham: Springer."},{"key":"9740_CR20","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9533996","author":"H Spieker","year":"2021","unstructured":"Spieker, H. (2021). Constraint-guided reinforcement learning: Augmenting the agent-environment-interaction. International Joint Conference on Neural Networks (IJCNN). https:\/\/doi.org\/10.1109\/IJCNN52387.2021.9533996","journal-title":"International Joint Conference on Neural Networks (IJCNN)"},{"key":"9740_CR21","unstructured":"Kalweit, G., Huegle, M., Werling, M., & Boedecker, J. (2020). Deep constrained q-learning. arXiv preprint arXiv:2003.09398."},{"key":"9740_CR22","unstructured":"Achiam, J., Held, D., Tian, A., & Abbeel, P. (2017). Constrained policy optimization. In Proceedings of the 34th International Conference on Machine Learning, (pp. 22\u201331)."},{"issue":"2","key":"9740_CR23","doi-asserted-by":"publisher","first-page":"1292","DOI":"10.1109\/TETCI.2025.3529902","volume":"9","author":"X Zhou","year":"2025","unstructured":"Zhou, X., Yuan, Y., Yang, S., & Hao, J. (2025). Mentor: Guiding hierarchical reinforcement learning with human feedback and dynamic distance constraint. IEEE Transactions on Emerging Topics in Computational Intelligence, 9(2), 1292\u20131306. https:\/\/doi.org\/10.1109\/TETCI.2025.3529902","journal-title":"IEEE Transactions on Emerging Topics in Computational Intelligence"},{"key":"9740_CR24","unstructured":"Miryoosefi, S., & Jin, C. (2022). A simple reward-free approach to constrained reinforcement learning. In K. Chaudhuri, S. Jegelka, L. Song, C. Szepesvari, G. Niu, & S. Sabato, (eds.), Proceedings of the 39th International Conference on Machine Learning. Proceedings of Machine Learning Research, (vol. 162, pp. 15666\u201315698). PMLR, Online. https:\/\/proceedings.mlr.press\/v162\/miryoosefi22a.html."},{"key":"9740_CR25","unstructured":"Zabounidis, R., Campbell, J., Stepputtis, S., Hughes, D., & Sycara, K.P. (2023). Concept learning for interpretable multi-agent reinforcement learning. In K. Liu, D. Kulic, & J. Ichnowski, (eds.), Proceedings of The 6th Conference on Robot Learning. Proceedings of Machine Learning Research, (vol. 205, pp. 1828\u20131837). PMLR, Online. https:\/\/proceedings.mlr.press\/v205\/zabounidis23a.html."},{"key":"9740_CR26","unstructured":"Iturria-Rivera, P.E., Gaigalas, R., Elsayed, M.H.M., Bavand, M., Ozcan, Y., & Erol-Kantarci, M. (2024). Explainable multi-agent reinforcement learning for extended reality codec adaptation. Arxiv:2411.14264 ."},{"issue":"5","key":"9740_CR27","doi-asserted-by":"publisher","first-page":"4090","DOI":"10.1109\/TPAMI.2025.3540467","volume":"47","author":"Z Liu","year":"2025","unstructured":"Liu, Z., Zhu, Y., Wang, Z., Gao, Y., & Chen, C. (2025). Mixrts: Toward interpretable multi-agent reinforcement learning via mixing recurrent soft decision trees. IEEE Transactions on Pattern Analysis and Machine Intelligence., 47(5), 4090\u20134107. https:\/\/doi.org\/10.1109\/TPAMI.2025.3540467","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence."},{"key":"9740_CR28","unstructured":"Poupart, Y., Beynier, A., & Maudet, N. (2025). Perspectives for direct interpretability in multi-agent deep reinforcement learning. arxiv:2502.00726."},{"key":"9740_CR29","unstructured":"Li, P., Siddique, U., & Cao, Y. (2025). From explainability to interpretability: Interpretable policies in reinforcement learning via model explanation. arxiv:2501.09858."},{"key":"9740_CR30","unstructured":"Berenji, H.R., & Vengerov, D. (2000). Learning, cooperation, and coordination in multi-agent systems. Technical Report IIS-00-10, Intelligent Inference Systems Corporation, Sunnyvale, CA, USA. White paper. https:\/\/citeseerx.ist.psu.edu\/document?repid=rep1&type=pdf&doi=c9e7a0e373ee4396b966c7485ccbe68d393f2e32."},{"key":"9740_CR31","doi-asserted-by":"publisher","unstructured":"Carrera, \u00c1., & glesias, C.A. (2011). Multi-agent architecture for heterogeneous reasoning under uncertainty combining MSBN and ontologies in distributed network diagnosis. In O. Boissier, J. Bradshaw, L. Cao, K. Fischer, & M. Hacid, (eds.), Proceedings of the 2011 IEEE\/WIC\/ACM International Conference on Intelligent Agent Technology, IAT 2011, Campus Scientifique de la Doua, Lyon, France, August 22\u201327, 2011, (pp. 159\u2013162) IEEE Computer Society, Online. https:\/\/doi.org\/10.1109\/WI-IAT.2011.106.","DOI":"10.1109\/WI-IAT.2011.106."},{"key":"9740_CR32","unstructured":"Serrino, J., Kleiman-Weiner, M., Parkes, D.C., & Tenenbaum, J. (2019). Finding friend and foe in multi-agent games. In H.M. Wallach, H. Larochelle, A. Beygelzimer, F. d\u2019Alch\u00e9-Buc, E.B. Fox, & R. Garnett, (eds.), Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8\u201314, 2019, Vancouver, BC, Canada, (pp. 1249\u20131259)."},{"key":"9740_CR33","doi-asserted-by":"publisher","unstructured":"Oliehoek, F.A., & Amato, C. (2016). A concise introduction to decentralized POMDPs. Springer Briefs in Intelligent Systems. Springer, Online. https:\/\/doi.org\/10.1007\/978-3-319-28929-8.","DOI":"10.1007\/978-3-319-28929-8"},{"key":"9740_CR34","doi-asserted-by":"publisher","unstructured":"Matignon, L., Laurent, G.J., & Le Fort-Piat, N. (2007). Hysteretic q-learning : an algorithm for decentralized reinforcement learning in cooperative multi-agent teams. In 2007 IEEE\/RSJ Int. Conf. on Intelligent Robots and Systems, (pp. 64\u201369). https:\/\/doi.org\/10.1109\/IROS.2007.4399095.","DOI":"10.1109\/IROS.2007.4399095."},{"key":"9740_CR35","unstructured":"Yuan, L., Zhang, Z., Li, L., Guan, C., & Yu, Y. (2023). A survey of progress on cooperative multi-agent reinforcement learning in open environment. arxiv:2312.01058."},{"issue":"3\u20134","key":"9740_CR36","doi-asserted-by":"publisher","first-page":"370","DOI":"10.1504\/IJAOSE.2007.016266","volume":"1","author":"JF Hubner","year":"2007","unstructured":"Hubner, J. F., Sichman, J. S., & Boissier, O. (2007). Developing organised multiagent systems using the moise+ model: programming issues at the system and agent levels. International Journal of Agent-Oriented Software Engineering, 1(3\u20134), 370\u2013395. https:\/\/doi.org\/10.1504\/IJAOSE.2007.016266","journal-title":"International Journal of Agent-Oriented Software Engineering"},{"key":"9740_CR37","doi-asserted-by":"crossref","unstructured":"Alshiekh, M., Bloem, R., Ehlers, R., K\u00f6nighofer, B., Niekum, S., & Topcu, U. (2018). Safe reinforcement learning via shielding. In Proceedings of the AAAI Conference on Artificial Intelligence, (vol. 32).","DOI":"10.1609\/aaai.v32i1.11797"},{"key":"9740_CR38","doi-asserted-by":"crossref","unstructured":"Marom, O., Rosman, B. (2018). Belief reward shaping in reinforcement learning. In Proceedings of the AAAI Conference on Artificial Intelligence, (vol. 32).","DOI":"10.1609\/aaai.v32i1.11741"},{"key":"9740_CR39","unstructured":"Carroll, M., Shah, R., Ho, M., Griffiths, T., Abbeel, P., & Dragan, A. (2020). Overcooked-ai: A benchmark for multi-agent learning under partial observability. In Proceedings of the 2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), (pp. 2374\u20132380)."},{"key":"9740_CR40","unstructured":"Ha, D., & Schmidhuber, J. (2018). Recurrent world models facilitate policy evolution. In S. Bengio, H. Wallach, H. Larochelle, K. Grauman, N. Cesa-Bianchi, & R. Garnett, (eds.), Advances in Neural Information Processing Systems, (vol. 31). Curran Associates Inc, Online."},{"key":"9740_CR41","unstructured":"Hafner, D., Lillicrap, T.P., Ba, J., & Norouzi, M. (2019). Dream to control: Learning behaviors by latent imagination. arxiv:1912.01603."},{"key":"9740_CR42","unstructured":"Moerland, T.M., Broekens, J., & Jonker, C.M. (2020). Model-based reinforcement learning: A survey. arxiv:2006.16712."},{"issue":"8","key":"9740_CR43","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/NECO.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735\u20131780. https:\/\/doi.org\/10.1162\/NECO.1997.9.8.1735","journal-title":"Neural Computation"},{"key":"9740_CR44","unstructured":"Pinto, L., Davidson, J., Sukthankar, R., & Gupta, A. (2017). Robust adversarial reinforcement learning. In Proceedings of the 34th International Conference on Machine Learning, (pp. 2817\u20132826). PMLR."},{"key":"9740_CR45","doi-asserted-by":"crossref","unstructured":"Tobin, J., Fong, R., Ray, A., Schneider, J., Zaremba, W., & Abbeel, P. (2017). Domain randomization for transferring deep neural networks from simulation to the real world. In 2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), (pp. 23\u201330). IEEE.","DOI":"10.1109\/IROS.2017.8202133"},{"issue":"1","key":"9740_CR46","first-page":"2096","volume":"17","author":"Y Ganin","year":"2016","unstructured":"Ganin, Y., Ustinova, E., Ajakan, H., Germain, P., Larochelle, H., Laviolette, F., Marchand, M., & Lempitsky, V. (2016). Domain-adversarial training of neural networks. Journal of Machine Learning Research., 17(1), 2096\u20132030.","journal-title":"Journal of Machine Learning Research."},{"key":"9740_CR47","unstructured":"Deisenroth, M.P., & Rasmussen, C.E. (2011). Pilco: A model-based and data-efficient approach to policy search. In Proceedings of the 28th International Conference on Machine Learning (ICML-11), (pp. 465\u2013472)."},{"key":"9740_CR48","first-page":"315","volume":"24","author":"S Hu","year":"2023","unstructured":"Hu, S., Zhong, Y., Gao, M., Wang, W., Dong, H., Liang, X., Li, Z., Chang, X., & Yang, Y. (2023). Marllib: A scalable and efficient multi-agent reinforcement learning library. Journal of Machine Learning Research, 24, 315\u2013131523.","journal-title":"Journal of Machine Learning Research"},{"key":"9740_CR49","doi-asserted-by":"publisher","unstructured":"Akiba, T., Sano, S., Yanase, T., Ohta, T., & Koyama, M. (2019). Optuna: A Next-generation Hyperparameter Optimization Framework. https:\/\/doi.org\/10.48550\/arxiv.1907.10902.","DOI":"10.48550\/arxiv.1907.10902."},{"key":"9740_CR50","doi-asserted-by":"publisher","unstructured":"Boissier, O., H\u00fcbner, J.F.,& Ricci, A. (2016). In H. Aldewereld, O. Boissier, V. Dignum, P. Noriega, & J. Padget, (eds.), The JaCaMo Framework, (pp. 125\u2013151). Springer, Cham. https:\/\/doi.org\/10.1007\/978-3-319-33570-4_7.","DOI":"10.1007\/978-3-319-33570-4_7."},{"key":"9740_CR51","unstructured":"Paszke, A., et. al. (2019). Pytorch: An imperative style, high-performance deep learning library. In H. Wallach, H. Larochelle, A. Beygelzimer, F. d\u2019Alche-Buc, E. Fox, & R. Garnett, (eds.), Advances in Neural Information Processing Systems, (vol. 32). Curran Associates Inc, Online."},{"issue":"9","key":"9740_CR52","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3022670.2976746","volume":"51","author":"M Abadi","year":"2016","unstructured":"Abadi, M. (2016). Tensorflow: learning functions at scale. SIGPLAN Notice, 51(9), 1. https:\/\/doi.org\/10.1145\/3022670.2976746","journal-title":"SIGPLAN Notice"},{"key":"9740_CR53","unstructured":"Soul\u00e9, J. (2024). Warehouse Management. GitHub. https:\/\/github.com\/julien6\/OMARLE."},{"key":"9740_CR54","unstructured":"Lowe, R., Wu, Y., Tamar, A., Harb, J., Abbeel, P., & Mordatch, I. (2017). Multi-agent actor-critic for mixed cooperative-competitive environments. In I. Guyon, U. Luxburg, S. Bengio, H.M. Wallach, R. Fergus, S.V.N. Vishwanathan, & R. Garnett, (eds.), Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4\u20139, 2017, Long Beach, CA, USA, (pp. 6379\u20136390). https:\/\/proceedings.neurips.cc\/paper\/2017\/hash\/68a9750337a418a86fe06c1991a1d64c-Abstract.html."},{"key":"9740_CR55","unstructured":"Carroll, M., Shah, R., Ho, M.K., Griffiths, T., Seshia, S., Abbeel, P., & Dragan, A. (2019). On the utility of learning about humans for human-ai coordination. In H. Wallach, H. Larochelle, A. Beygelzimer, F. Alch\u00e9-Buc, E. Fox, & R. Garnett, (eds.), Advances in Neural Information Processing Systems, (vol. 32). Curran Associates Inc, Online."},{"key":"9740_CR56","unstructured":"Standen, M., Lucas, M., Bowman, D., Richer, T.J., Kim, J., & Marriott, D. (2021). Cyborg: A gym for the development of autonomous cyber agents. arxiv:2108.09118."}],"container-title":["Autonomous Agents and Multi-Agent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10458-026-09740-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10458-026-09740-0","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10458-026-09740-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T09:25:28Z","timestamp":1775899528000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10458-026-09740-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,11]]},"references-count":56,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,6]]}},"alternative-id":["9740"],"URL":"https:\/\/doi.org\/10.1007\/s10458-026-09740-0","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-7166037\/v1","asserted-by":"object"}]},"ISSN":["1387-2532","1573-7454"],"issn-type":[{"value":"1387-2532","type":"print"},{"value":"1573-7454","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,11]]},"assertion":[{"value":"19 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 February 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 April 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"Not applicable.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Materials availability"}},{"value":"The authors declare no competing interests.","order":6,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"20"}}