{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T14:02:38Z","timestamp":1782741758744,"version":"3.54.5"},"reference-count":40,"publisher":"Association for Computing Machinery (ACM)","issue":"2","license":[{"start":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T00:00:00Z","timestamp":1782691200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100021171","name":"Guangdong Basic and Applied Basic Research Foundation","doi-asserted-by":"crossref","award":["2024B1515020019"],"award-info":[{"award-number":["2024B1515020019"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Evol. Learn. Optim."],"published-print":{"date-parts":[[2026,6,30]]},"abstract":"<jats:p>\n                    The NeuroEvolution of Augmenting Topologies (NEAT) algorithm has received considerable recognition in the field of neuroevolution. Its effectiveness is derived from initiating with simple networks and incrementally evolving both their topologies and weights. Although its capability across various challenges is evident, the algorithm\u2019s computational efficiency remains an impediment, limiting its scalability potential. To address these limitations, this article introduces TensorNEAT, a GPU-accelerated library that applies tensorization to the NEAT algorithm. Tensorization reformulates NEAT\u2019s diverse network topologies and operations into uniformly shaped tensors, enabling efficient parallel execution across entire populations. TensorNEAT is built upon JAX, leveraging automatic function vectorization and hardware acceleration to significantly enhance computational efficiency. In addition to NEAT, the library supports variants such as CPPN and HyperNEAT and integrates with benchmark environments like Gym, Brax, and gymnax. Experimental evaluations across various robotic control environments in Brax demonstrate that TensorNEAT delivers up to 500\u00d7 speedups compared to existing implementations, such as NEAT-Python. The source code for TensorNEAT is publicly available at:\n                    <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/EMI-Group\/tensorneat\">https:\/\/github.com\/EMI-Group\/tensorneat<\/jats:ext-link>\n                    .\n                  <\/jats:p>","DOI":"10.1145\/3730406","type":"journal-article","created":{"date-parts":[[2025,4,16]],"date-time":"2025-04-16T12:37:50Z","timestamp":1744807070000},"page":"1-31","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["TensorNEAT: A GPU-accelerated Library for NeuroEvolution of Augmenting Topologies"],"prefix":"10.1145","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-2374-8699","authenticated-orcid":false,"given":"Lishuang","family":"Wang","sequence":"first","affiliation":[{"name":"Southern University of Science and Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1653-8553","authenticated-orcid":false,"given":"Mengfei","family":"Zhao","sequence":"additional","affiliation":[{"name":"Southern University of Science and Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5645-8578","authenticated-orcid":false,"given":"Enyu","family":"Liu","sequence":"additional","affiliation":[{"name":"Southern University of Science and Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9213-7835","authenticated-orcid":false,"given":"Kebin","family":"Sun","sequence":"additional","affiliation":[{"name":"Southern University of Science and Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9410-8263","authenticated-orcid":false,"given":"Ran","family":"Cheng","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University, Hong Kong SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,29]]},"reference":[{"key":"e_1_3_1_2_1","first-page":"265","volume-title":"Proceedings of the 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI \u201916)","author":"Abadi Mart\u00edn","year":"2016","unstructured":"Mart\u00edn Abadi, Paul Barham, Jianmin Chen, Zhifeng Chen, Andy Davis, Jeffrey Dean, Matthieu Devin, Sanjay Ghemawat, Geoffrey Irving, Michael Isard, et al. 2016. TensorFlow: A system for large-scale machine learning. In Proceedings of the 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI \u201916), 265\u2013283."},{"key":"e_1_3_1_3_1","doi-asserted-by":"crossref","first-page":"1475","DOI":"10.1145\/2001576.2001775","volume-title":"Proceedings of the Annual Conference on Genetic and Evolutionary Computation","author":"Auerbach Joshua E.","year":"2011","unstructured":"Joshua E. Auerbach and Josh C. Bongard. 2011. Evolving complete robots with CPPN-NEAT: The utility of recurrent connections. In Proceedings of the Annual Conference on Genetic and Evolutionary Computation, 1475\u20131482."},{"key":"e_1_3_1_4_1","unstructured":"b2developer. 2022. MonopolyNEAT: NEAT Implemented into Monopoly with a Knockout Tournament Scheme. Retrieved August 15 2023 from https:\/\/github.com\/b2developer\/MonopolyNEAT"},{"key":"e_1_3_1_5_1","unstructured":"Greg Brockman Vicki Cheung Ludwig Pettersson Jonas Schneider John Schulman Jie Tang and Wojciech Zaremba. 2016. OpenAI Gym. arXiv:1606.01540. Retrieved from https:\/\/arxiv.org\/abs\/1606.01540"},{"key":"e_1_3_1_6_1","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared D. Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et al. 2020. Language models are few-shot learners. In Proceedings of the 34th International Conference on Neural Information Processing Systems 1877\u20131901."},{"key":"e_1_3_1_7_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1000187"},{"key":"e_1_3_1_8_1","volume-title":"Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks","author":"Freeman C. Daniel","year":"2021","unstructured":"C. Daniel Freeman, Erik Frey, Anton Raichuk, Sertan Girgin, Igor Mordatch, and Olivier Bachem. 2021. Brax\u2013A differentiable physics engine for large scale rigid body simulation. In Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks."},{"key":"e_1_3_1_9_1","unstructured":"James Bradbury Roy Frostig Peter Hawkins Matthew James Johnson Chris Leary Dougal Maclaurin George Necula Adam Paszke Jake VanderPlas Skye Wanderman-Milne et al. 2018. JAX: composable transformations of Python+NumPy programs. Version 0.3.13. Retrieved from http:\/\/github.com\/jax-ml\/jax"},{"key":"e_1_3_1_10_1","unstructured":"Alex Gajewsky. 2023. PyTorch NEAT. Retrieved August 7 2023 from https:\/\/github.com\/uber-research\/PyTorch-NEAT"},{"key":"e_1_3_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3449726.3459509"},{"key":"e_1_3_1_12_1","doi-asserted-by":"publisher","DOI":"10.1142\/S0129065709002002"},{"key":"e_1_3_1_13_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-2649-2"},{"key":"e_1_3_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2024.3388550"},{"key":"e_1_3_1_15_1","doi-asserted-by":"publisher","DOI":"10.5555\/3157382.3157557"},{"key":"e_1_3_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/368996.369025"},{"key":"e_1_3_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3512290.3528706"},{"key":"e_1_3_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3583131.3590496"},{"key":"e_1_3_1_19_1","unstructured":"Robert Tjarko Lange. 2022. gymnax: A JAX-Based Reinforcement Learning Environment Library. Retrieved from http:\/\/github.com\/RobertTLange\/gymnax"},{"key":"e_1_3_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3583133.3590733"},{"key":"e_1_3_1_21_1","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1145\/2001576.2001606","volume-title":"Proceedings of the Annual Conference on Genetic and Evolutionary Computation","author":"Lehman Joel","year":"2011","unstructured":"Joel Lehman and Kenneth O. Stanley. 2011. Evolving a diversity of creatures through novelty search and local competition. In Proceedings of the Annual Conference on Genetic and Evolutionary Computation, 211\u2013218."},{"key":"e_1_3_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3520304.3528927"},{"key":"e_1_3_1_23_1","unstructured":"Alan McIntyre Matt Kallada Cesar G. Miguel Carolina Feher de Silva and Marcio Lobo Netto. 2023. Python implementation of the NEAT neuroevolution algorithm. Retrieved August 7 2023 from https:\/\/github.com\/CodeReclaimers\/neat-python"},{"key":"e_1_3_1_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-12-815480-9.00015-3"},{"key":"e_1_3_1_25_1","unstructured":"Jean-Baptiste Mouret and Jeff Clune. 2015. Illuminating search spaces by mapping elites. arXiv:1504.04909. Retrieved from https:\/\/arxiv.org\/abs\/1504.04909"},{"key":"e_1_3_1_26_1","first-page":"8024","volume-title":"Advances in Neural Information Processing Systems","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et al. 2019. PyTorch: An imperative style, high-performance deep learning library. In Advances in Neural Information Processing Systems. H. Wallach, H. Larochelle, A. Beygelzimer, F. d\u2019Alch\u00e9 Buc, E. Fox, and R. Garnett (Eds.), Curran Associates, Inc., 8024\u20138035. Retrieved from http:\/\/papers.neurips.cc\/paper\/9015-pytorch-an-imperative-style-high-performance-deep-learning-library.pdf"},{"key":"e_1_3_1_27_1","unstructured":"peter-ch. 2019. MultiNEAT: Portable NeuroEvolution Library. Retrieved August 15 2023 from https:\/\/github.com\/peter-ch\/MultiNEAT"},{"key":"e_1_3_1_28_1","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence\u2014Student Abstract Track","volume":"32","author":"Pham Son","year":"2018","unstructured":"Son Pham, Keyi Zhang, Tung Phan, Jasper Ding, and Christopher Dancy. 2018. Playing SNES games with neuroevolution of augmenting topologies. In Proceedings of the AAAI Conference on Artificial Intelligence\u2014Student Abstract Track, Vol. 32."},{"key":"e_1_3_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3512290.3528744"},{"key":"e_1_3_1_30_1","doi-asserted-by":"crossref","first-page":"563","DOI":"10.1145\/1830483.1830589","volume-title":"Proceedings of the Annual Conference on Genetic and Evolutionary Computation","author":"Risi Sebastian","year":"2010","unstructured":"Sebastian Risi, Joel Lehman, and Kenneth O. Stanley. 2010. Evolving the placement and density of neurons in the HyperNEAT substrate. In Proceedings of the Annual Conference on Genetic and Evolutionary Computation, 563\u2013570."},{"key":"e_1_3_1_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-72699-7_45"},{"key":"e_1_3_1_32_1","doi-asserted-by":"publisher","DOI":"10.1162\/978-0-262-31050-5-ch034"},{"key":"e_1_3_1_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10710-007-9028-8"},{"key":"e_1_3_1_34_1","first-page":"1671","volume-title":"Proceedings of the 21st National Conference on Artificial Intelligence","volume":"2","author":"Stanley Kenneth O.","year":"2006","unstructured":"Kenneth O. Stanley, Bobby D. Bryant, Igor Karpov, and Risto Miikkulainen. 2006. Real-time evolution of neural networks in the NERO video game. In Proceedings of the 21st National Conference on Artificial Intelligence, Vol. 2. AAAI Press, 1671\u20131674."},{"key":"e_1_3_1_35_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-018-0006-z"},{"key":"e_1_3_1_36_1","doi-asserted-by":"publisher","DOI":"10.1162\/artl.2009.15.2.15202"},{"key":"e_1_3_1_37_1","doi-asserted-by":"publisher","DOI":"10.1162\/106365602320169811"},{"key":"e_1_3_1_38_1","unstructured":"Felipe Petroski Such Vashisht Madhavan Edoardo Conti Joel Lehman Kenneth O. Stanley and Jeff Clune. 2018. Deep neuroevolution: Genetic algorithms are a competitive alternative for training deep neural networks for reinforcement learning. arXiv:1712.06567. Retrieved from https:\/\/arxiv.org\/abs\/1712.06567"},{"key":"e_1_3_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3520304.3528770"},{"key":"e_1_3_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3638529.3654210"},{"key":"e_1_3_1_41_1","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1016\/j.aei.2017.11.003","article-title":"Agent-based evacuation modeling with multiple exits using NeuroEvolution of augmenting topologies","volume":"35","author":"Yuksel Mehmet Erkan","year":"2018","unstructured":"Mehmet Erkan Yuksel. 2018. Agent-based evacuation modeling with multiple exits using NeuroEvolution of augmenting topologies. Advanced Engineering Informatics 35 (2018), 30\u201355.","journal-title":"Advanced Engineering Informatics"}],"container-title":["ACM Transactions on Evolutionary Learning and Optimization"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3730406","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T13:32:42Z","timestamp":1782739962000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3730406"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,29]]},"references-count":40,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,6,30]]}},"alternative-id":["10.1145\/3730406"],"URL":"https:\/\/doi.org\/10.1145\/3730406","relation":{},"ISSN":["2688-299X","2688-3007"],"issn-type":[{"value":"2688-299X","type":"print"},{"value":"2688-3007","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,29]]},"assertion":[{"value":"2024-10-02","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-03-27","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-06-29","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}