Evolutionary AI Research Publications

    2025

  1. Risi, S., Ha, D, Tang, Y., and Miikkulainen, R. (in press). Neuroevolution: Harnessing Creativity in AI Model Design. Cambridge, MA: MIT Press.

  2. Meyerson, E. and Qiu, X. (2025). Position: Scaling LLM Agents Requires Asymptotic Analysis with LLM Primitives. In Proceedings of the International Conference on Machine Learning (also arXiv:2502.04358).

  3. Warner, J. and Miikkulainen, R. (2025). Self-Organizing Models of Brain Wiring: Developmental Programs for Evolving Intelligence. In Proceedings of the Genetic and Evolutionary Computation Conference Companion: Workshop on Evolution and Self-organization.

  4. Shahrzad, H. an Miikkulainen, R. (2025). GPU-Accelerated Rule Evaluation and Evolution. In Proceedings of the Genetic and Evolutionary Computation Conference Companion: Workshop on Evolutionary Rule-based Machine Learning (also arXiv:2406.01821).

  5. Gonzalez, S. and Miikkulainen, R. (2025). Effective Regularization Through Loss-Function Metalearning. In Proceedings of the 2025 IEEE Congress on Evolutionary Computation (also arXiv:2010.00788).

  6. Miikkulainen, R., Smith, J., and Hodjat, B. (2025). Learning from the Past: How Previous Technological Transformations Can Guide AI Development. arXiv:1905.13178.

  7. Young, D., Francon, O., Meyerson, E., Schwingshackl, C., Bieker, J., Cunha, H.,Hodjat, B., and Miikkulainen, R. (2025). Discovering Effective Policies for Land-Use Planning. Environmental Data Science 4:e30 (also arXiv:2311.12304).
    A shorter version appeared in the Proceedings of the NeurIPS 2023 Workshop on Tackling Climate Change with Machine Learning.
    Best Pathway to Impact Award (at the workshop).
    Presentation video (at the workshop).

  8. Miikkulainen, R. (2025). Neuroevolution Insights Into Biological Neural Computation. Science 387, eadp 7478.

  9. Lehman, J., Meyerson, E., El-Gaaly, T., Stanley, K. O., and Ziyaee, T. (2025). Evolution and The Knightian Blindspot of Machine Learning. arXiv:2501.13075.

    10. 2024

  10. Havrilla, A., Dai, A., O’Mahony, L., Oostermeijer, K, Zisler, V., Albalak, A., Milo, F., Raparthy, S. C., Gandhi, K., Abbasi, B., Phung, D., Iyer, M., Mahan, D., Blagden, C., Gureja, S., Hamdy, M. Li, W.-D., Paolini, G. Ammanamanchi, P. S., Meyerson, E. (2024). Surveying the Effects of Quality, Diversity, and Complexity in Synthetic Data From Large Language Models. arXiv:2412.02980.

  11. Shahrzad, H., Hodjat, B., and Miikkulainen, R. (2024). EVOTER: Evolution of Transparent Explainable Rule-sets. ACM Transactions on Evolutionary Learning and Optimization (also arXiv:2204.10438).

  12. Meyerson, E., Francon, O., Sargent, D., Hodjat, B., and Miikkulainen, R. (2024). Unlocking the Potential of Global Human Expertise. In Proceedings of the 38th Conference on Neural Information Processing Systems (NeurIPS 2024).
    Presentation video.

  13. Qiu, X., and Miikkulainen, R. (2024). Semantic Density: Uncertainty Quantification for Large Language Models through Confidence Measurement in Semantic Space. In Proceedings of the 38th Conference on Neural Information Processing Systems (NeurIPS 2024). (also arXiv:2405.13845).
    Presentation video.

  14. GPAI (2024). Pandemic Resilience: Case Studies of an AI-calibrated Ensemble of Models to Inform Decision Making. Report, November 2024, GPAI: The Global Partnership on Artificial Intelligence.

  15. Meyerson, E., Nelson, M. J., Bradley, H., Gaier, A., Moradi, A., Hoover, A. K., and Lehman, J. (2024). Language Model Crossover: Variation through Few-Shot Prompting. ACM Transactions on Evolutionary Learning and Optimization (also arXiv:2302.12170).

  16. Nisioti, E., Glanois, G., Najarro, E., Dai, A., Meyerson, E., Pedersen, J. W., Teodorescu, L., Hayes, C.F., Sudhakaran, S., and Risi. S. (2024). From Text to Life: On the Reciprocal Relationship between Artificial Life and Large Language Models. Proceedings of the 2024 Artificial Life Conference, pp. 39. https://doi.org/10.1162/isal_a_00759

  17. Bai, G., Dhillon, N., Felton, C., Meissner, B., Saint-John, B., Shelansky, R., Meyerson, E., Hrabeta-Robinson, E., Hodjat, B., Boeger, H., Brooks, A. N. (2024). Probing chromatin accessibility with small molecule DNA intercalation and nanopore sequencing. bioRxiv 2024.03.20.585815

  18. Hodjat, B. (2024). AI and Agents. AI Magazine 1-3. https://doi.org/10.1002/aaai.12170.
    Video abstract (i.e. a discussion with Risto Miikkulainen)

  19. Miikkulainen, R. (2024). Generative AI: An AI Paradigm Shift in the Making? AI Magazine 1-3. https://doi.org/10.1002/aaai.12155.
    Video abstract (i.e. a discussion with Babak Hodjat)

  20. Khanna, A., Francon, O., and Miikkulainen, R. (2024). Optimizing the Design of an Artificial Pancreas to Improve Diabetes Management. arXiv:2402.07949.

  21. Liang, J., Shahrzad, H., and Miikkulainen, R. (2024). Asynchronous Evolution of Deep Neural Network Architectures. Applied Soft Computing 152:111209 (also arXiv:2308.04102).

  22. Hodjat, B., Shahrzad, H., and Miikkulainen, R. (2024). Domain-Independent Lifelong Problem Solving through Distributed Alife Actors. Artificial Life 30:259-276.

    23. 2023

  23. GPAI (2023). Pandemic Resilience: Developing an AI-calibrated Ensemble of Models to Inform Decision Making. Report, December 2023, GPAI: The Global Partnership on Artificial Intelligence.

  24. Miikkulainen, R. (2023). Evolutionary Supervised Machine Learning. In W. Banzhaf, P. Machado, and M. Zhang (editors), Handbook of Evolutionary Machine Learning. Springer, New York.

  25. Shahrzad, H. and Miikkulainen, R. (2023). Accelerating Evolution Through Gene Masking and Distributed Search. In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO-2023, Lisbon, Portugal; also arXiv:2302.06745).

  26. Qiu, X., and Miikkulainen, R. (2023). Shortest Edit Path Crossover: A Theory-driven Solution to the Permutation Problem in Evolutionary Neural Architecture Search. In Proceedings of the International Conference on Machine Learning (ICML-2023, Honolulu, HI; also arXiv:2210.14016).

  27. Bingham, G. and Miikkulainen, R. (2023). Efficient Activation Function Optimization through Surrogate Modeling. In Proceedings of the 37th Conference on Neural Information Processing Systems (NeurIPS 2023, New Orleans, LA; also arXiv:2301.05785).
    Presentation video.

  28. Bingham, G. and Miikkulainen, R. (2023). AutoInit: Analytic Signal-Preserving Weight Initialization for Neural Networks. In Proceedings of the 37th AAAI Conference on Artificial Intelligence (AAAI-2023, Washington, DC; also arXiv:2109.08958).
    Presentation video.

  29. Gonzalez, S., Kant, M., and Miikkulainen, R. (2023). Evolving GAN Formulations for Higher Quality Image Synthesis.  In Kozma, R., Alippi, C., Choe, Y., and Morabito, F. C., Artificial Intelligence in the Age of Neural Networks and Brain Computing. Second Edition. New York: Elsevier. (also arXiv:2102.08578).

  30. Miikkulainen, R., Meyerson, E., Liang, J., Rawal, A., Shahrzad, H., Fink, D. Francon, O., Raju, B., Navruzyan, A., Hodjat, B., and Duffy, N. (2023). Evolving Deep Neural Networks. In Kozma, R., Alippi, C., Choe, Y., and Morabito, F. C., Artificial Intelligence in the Age of Neural Networks and Brain Computing. Second Edition. New York: Elsevier.

    31. 2022

  31. Miikkulainen, R. (2022). Neuroevolution. In Phung, D., Sammut, C. and Webb, G. I. (editors), Encyclopedia of Machine Learning and Data Science, 3rd Edition. Berlin: Springer.

  32. Hodjat, B., Shahrzad, H., and Miikkulainen, R. (2022). DIAS: A Domain-Independent Alife-Based Problem-Solving System. In Proceedings of the 2022 Conference on Artificial Life (also arXiv:2203.06855).

  33. Meyerson, E, Qiu, X, and Miikkulainen, R. (2022). Simple Genetic Operators are Universal Approximators of Probability Distributions (and other Advantages of Expressive Encodings). In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO-2022), 739-748 (also arXiv:2202.09679).
    Best-paper award in the GA track.
    Presentation video.

  34. Bingham, G. and Miikkulainen, R. (2022). Discovering Parametric Activation Functions. Neural Networks 148:48-65 (also arXiv:2006.03179).
    Best-Paper Award for papers published in Neural Networks in 2022.

  35. Qiu, X. and Miikkulainen, R. (2022). Detecting Misclassification Errors in Neural Networks with a Gaussian Process Model. In Proceedings of the 36th AAAI Conference on Artificial Intelligence (AAAI-2022; also arXiv:2010.02065).

    36. 2021

  36. Miikkulainen, R., Francon, O. Meyerson, E., Qiu, X., Sargent, D., Canzani, E., and Hodjat, B. (2021). From Prediction to Prescription: Evolutionary Optimization of Non-Pharmaceutical Interventions in the COVID-19 Pandemic. IEEE Transactions on Evolutionary Computation 25:386--401 (an earlier version in arXiv:2005.13766).

  37. Miikkulainen, R., Meyerson, E., Qiu, X., Sinha, U., Kumar, R., Hofmann, K., Yan, Y. M., Ye, M., Yang, J., Caiazza, D., Manson Brown, S. (2021). Evaluating Medical Aesthetics Treatments through Evolved Age-Estimation Models. In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO-2021), 1009–1017.
    Silver Award in the Human-Competitive Results Competition, GECCO-2022.
    Presentation video.

  38. Gonzalez, S. and Miikkulainen, R. (2021). Optimizing Loss Functions Through Multivariate Taylor Polynomial Parameterization. In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO-2021), 305-313 (also arXiv:2002.00059).
    Presentation video.

  39. Liang, J., Gonzalez, S., Shahrzad, H.,, and Miikkulainen, R. (2021). Regularized Evolutionary Population-Based Training. In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO-2021), 323–331 (also arXiv:2002.04225).
    Presentation video.

  40. Meyerson, E. and Miikkulainen, R. (2021). The Traveling Observer Model: Multi-task Learning Through Spatial Variable Embeddings. In Proceedings of the International Conference on Learning Representations (ICLR-2021; also arXiv:2010.02354).
    Presentation video.

  41. Miikkulainen, R. (2021). Creative AI Through Evolutionary Computation: Principles and Examples. SN Computer Science 2:163 (also arXiv:2008.04212).

  42. Miikkulainen R. and Forrest, S. (2021). A Biological Perspective on Evolutionary Computation. Nature Machine Intelligence, 3:9-15.

    43. 2020

  43. Francon, O., Gonzalez, S., Hodjat, B., Meyerson, E., B. Miikkulainen, R., Qiu, X., and Shahrzad, H. (2020). Effective Reinforcement Learning through Evolutionary Surrogate-Assisted Prescription. In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO-2020; also arXiv:2002.05368).
    Best-Paper Award in the GECH track.
    Presentation video.

  44. Bingham, G., Macke, W., and Miikkulainen, R. (2020). Evolutionary Optimization of Deep Learning Activation Functions. In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO-2020), 289-296 (also arXiv:2002.07224).
    Presentation video.

  45. Gonzalez, S. and Miikkulainen, R. (2020). Improved training speed, accuracy, and data utilization through loss-function optimization. In Proceedings of the 2020 IEEE Congress on Evolutionary Computation (CEC-2020), 1-8 (also arXiv:1905.11528).
    Presentation video.

  46. Jiang, J., Legrand, D., Severn, R., and Miikkulainen, R. (2020). A Comparison of the Taguchi Method and Evolutionary Optimization in Multivariate Testing. In Proceedings of the 2020 IEEE Congress on Evolutionary Computation (CEC-2020; also arXiv:1808.08347).
    Presentation video.

  47. Qiu, X., Meyerson, E., and Miikkulainen, R. (2020). Quantifying Point-Prediction Uncertainty in Neural Networks via Residual Estimation with an I/O Kernel.. In Proceedings of the International Conference on Learning Representations (ICLR-2020; also arXiv:1906.00588).
    Presentation video.

  48. Miikkulainen R., Brundage M., Epstein J., Foster, T., Hodjat, B., Iscoe N., Jiang, J., Legrand, D., Nazari S., Qiu, X., Scharff, M., Schoolland C., Severn, R., and Shagrin A. (2020). Ascend by Evolv: AI-Based Massively Multivariate Conversion Rate Optimization. AI Magazine 41:44-60

  49. Rawal, A. and Miikkulainen, R. (2020). Discovering Gated Recurrent Neural Network Architectures. In H. Iba and N. Noman (editors), Deep Neural Evolution – Deep Learning with Evolutionary Computation, 233-251. New York: Springer (also arXiv:1803.04439).

  50. Shahrzad, H., Hodjat, B., Dolle, C., Denissov, A., Lau, S., Goodhew, D., Dyer, J., and Miikkulainen, R. (2020). Enhanced Optimization with Composite Objectives and Novelty Pulsation. In Genetic Programming Theory and Practice XVII. Springer, New York (also arXiv:1906.04050).

  51. Miikkulainen, R. (2020). Creative AI Through Evolutionary Computation. In Banzhaf et al. (editors), Evolution in Action---Past, Present and Future. Springer, New York (also arXiv:1901.03775).

    52. 2019

  52. Meyerson, E. and Miikkulainen, R. (2019). Modular Universal Reparameterization: Deep Multi-task Learning Across Diverse Domains. In Proceedings of the 33rd Annual Conference on Neural Information Processing Systems (NeurIPS 2019, Vancouver, Canada; also arXiv:1906.00097).

  53. Liang, J., Meyerson, E., Fink, D., Mutch, K., and Miikkulainen, R. (2019). Evolutionary Neural AutoML for Deep Learning. In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO-2019, Prague, Czech Republic), 401–409 (also arXiv:1902.06827).

  54. Johnson, A. J., Meyerson, E., de la Parra, J., Savas, T. L., Miikkulainen, R., and Harper, C. B. (2019). Flavor-Cyber-Agriculture: Optimization of plant metabolites in an open-source control environment through surrogate modeling. bioRxiv 424226.

  55. Stanley, K. O., Clune, J., Lehman, J., and Miikkulainen R. (2019). Designing Neural Networks through Evolutionary Algorithms. Nature Machine Intelligence 1:24-35.

  56. Qiu, X. and Miikkulainen, R. (2019). Enhancing Evolutionary Optimization in Uncertain Environments via Multi-Armed Bandit Algorithms. In Proceedings of the 31st Innovative Applications of Artificial Intelligence Conference (IAAI-2019, Honolulu, HI; also arXiv:1803.03737).

    57. 2018

  57. Meyerson, E. and Miikkulainen, R. (2018). Pseudo-task Augmentation: From Deep Multitask Learning to Intratask Sharing—and Back. In Proceedings of the International Conference on Machine Learning (ICML-2018, Stockholm, Sweden), 739-748 (also arXiv:1803.04062).

  58. Shahrzad, H., Fink, D., and Miikkulainen, R. (2018). Enhanced Optimization with Composite Objectives and Novelty Selection. In Proceedings of the 2018 Conference on Artificial Life (ALife'2018, Tokyo, Japan; also arXiv:1803.03744).

  59. Liang, J., Meyerson, E., and Miikkulainen, R. (2018). Evolutionary Architecture Search for Deep Multitask Networks.  In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO-2018, Kyoto, Japan), 466-473 (also arXiv:1803.03745).

  60. Meyerson, E. and Miikkulainen, R. (2018). Beyond Shared Hierarchies: Deep Multitask Learning through Soft Layer Ordering. In Proceedings of the International Conference on Learning Representations, (ICLR-2018, Vancouver, Canada; also arXiv:1711.00108.).

  61. Miikkulainen, R., Meyerson, E., Liang, J., Rawal, A., Shahrzad, H., Fink, D. Francon, O., Raju, B., Navruzyan, A., Hodjat, B., and Duffy, N. (2019). Evolving Deep Neural Networks. In Kozma, R., Alippi, C., Choe, Y., and Morabito, F. C., Artificial Intelligence in the Age of Neural Networks and Brain Computing, 293-312. Amsterdam: Elsevier (also arXiv:1703.00548).

  62. Miikkulainen, R., Iscoe, N., Shagrin, A., Rapp, R., Nazari, S., McGrath, P., Schoolland, C., Achkar, E., Brundage, M., Miller, J., Epstein, and Lamba, G. (2018).  Sentient Ascend: AI-Based Massively Multivariate Conversion Rate Optimization. In Proceedings of the Thirtieth Innovative Applications of Artificial Intelligence Conference (IAAI-2018, New Orleans, LA).
    IAAI Deployed Application Award.

  63. Hodjat, B., Shahrzad, H., Miikkulainen, R., Murray, L., and Holmes, C. (2018). PRETSL: Distributed probabilistic rule evolution for time-series classification. In Genetic Programming Theory and Practice XIV. Springer, New York.

    64. 2017

  64. Miikkulainen, R., Shahrzad, H., Duffy, N., and Long, P. (2017). How to Select a Winner in Evolutionary Optimization? In Proceedings of the 2017 IEEE Symposium Series on Computational Intelligence. Piscataway, NJ: IEEE.

  65. Meyerson, E. and Miikkulainen, R. (2017). Discovering Evolutionary Stepping Stones through Behavior Domination. In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2017, Berlin, Germany).

  66. Miikkulainen, R., Iscoe, N., Shagrin, A., Cordell, R., Nazari, S., Schoolland, C., Brundage, M., Epstein, J., Dean, R. and Lamba, G. (2017). Conversion Rate Optimization through Evolutionary Computation. In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2017, Berlin, Germany; also arXiv:1703.00556).
    Bronze Medal, Human-Competitive Results Competition.

  67. Awasthi, P., Balcan M. F., and Long, P. M (2017).  The power of localization for efficiently learning linear separators with noise.  Journal of the ACM, 63(6):50:1-50:27.

    68. 2016

  68. Ramamurthy, V. and Duffy, N. (2016). L-SR1: A Novel Second Order Optimization Method for Deep Learning. (+ supplement). In NIPS 2016 Workshop on Nonconvex Optimization for Machine Learning: Theory and Practice.

  69. Legrand, D., Long, P. M., Brundage, M., Angelopoulos, T., Francon, O., Garg, V., Mann, W., Ramamurthy, V., Saliou, A., Simmons, B., Skipper, P., Tsatsin, P., Vistnes, R., Duffy, N. (2016). Visual Product Discovery. In the "Machine Learning Meets Fashion" Workshop at the 22nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining (San Francisco, CA).

  70. Hodjat, B., Shahrzad, H., and Miikkulainen, R. (2016). Distributed age-layered novelty search. In Proceedings of the Fifteenth International Conference on the Synthesis and Simulation of Living Systems (Alife'16, Cancun, Mexico).

  71. Shahrzad, H., Hodjat, B., and Miikkulainen, R. (2016). Estimating the advantage of age-layering in evolutionary algorithms. In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2016, Denver, CO).

  72. Hodjat, B. and Shahrzad, J. (2016). nPool: Massively distributed simultaneous evolution and cross-validation in EC-star. In Riolo, R., Worzel, W. P., Kotanchek, M., and Kordon, A. editors, Genetic Programming Theory and Practice XIII, Genetic and Evolutionary Computation. Springer, New York.

    73. 2015

  73. Shahrzad, H. and Hodjat, B. (2015). Tackling the Boolean multiplexer function using a highly distributed genetic programming system. In Riolo, R., Worzel, W. P., and Kotanchek, M., editors, Genetic Programming Theory and Practice XII, pages 167-179. Springer, New York.

    74. 2014

  74. Hodjat, B., Hemberg, E., Shahrzad, H., and O'Reilly, U.-M. (2014). Maintenance of a long running distributed genetic programming system for solving problems requiring big data. In Genetic Programming Theory and Practice XI, pages 65-83. Springer, New York.

  75. Hemberg, E., Veeramachaneni, K., Wanigasekara, P., Shahrzad, H., Hodjat, B., and O'Reilly, U.-M. (2014).  Learning Decision Lists with Lagged Physiological Time Series. In Workshop on Data Mining for Medicine and Healthcare at the 14th SIAM International Conference on Data Mining, pages 82--87.

    76. 2013

  76. Hodjat, B. and Shahrzad, H. (2013). Introducing an age-varying fitness estimation function. In Riolo, R., Vladislavleva, E., Ritchie, M. D., and Moore, J. H., editors, Genetic Programming Theory and Practice X, pages 59-71. Springer, New York.

  77. O'Reilly, U.-M., Wagy, M., and Hodjat, B. (2013). EC-Star: A massive-scale, hub and spoke, distributed genetic programming system. In Riolo, R., Vladislavleva, E., Ritchie, M. D., and Moore, J. H., editors, Genetic Programming Theory and Practice X, pages 73-85. Springer, New York.