Evolving self-organisation
Webpage: https://evolving-self-organisation-workshop.github.io/gecco-2026
Description
Recent dramatic advances in the problem-solving capabilities and scale of Artificial Intelligence (AI) systems have enabled their successful application in challenging real-world scientific and engineering problems (Abramson et al 2024, Lam et al 2023). Yet these systems remain brittle to small disturbances and adversarial attacks (Su et al 2019, Cully 2014), lack human-level generalisation capabilities (Chollet 2019), and require alarming amounts of human, energy and financial resources (Strubel et al 2019). This rapid scaling has pushed AI research toward exploring how artificial systems can be made more autonomous, resilient, and creative, ultimately aiming at automated human-level scientific discovery (Georgiev et al 2025). In this evolving landscape, evolutionary algorithms have been integrated with foundation models (Novikov et al 2025, Lange et al 2025), where the former provide a grounded evaluation mechanism and the latter accelerate search and introduce creative mutations.
Biological systems, on the other hand, seem to have largely solved many of these issues. They are capable of developing into complex organisms from a few cells and regenerating limbs through highly energy-efficient processes shaped by evolution. They do so through self-organisation: collectives of simple components interact locally with each other to give rise to macroscopic properties in the absence of centralised control (Camazine, 2001). This ability to self-organise renders organisms adaptive to their environments and robust to unexpected failures, as the redundancy built in the collective enables repurposing components, crucially, by leveraging the same self-organisation process that created the system in the first place. Thus, both evolution and self-organisation play an important role in creating and maintaining this impressive diversity of life.
Self-organisation lies at the core of many computational systems that exhibit properties such as robustness, adaptability, scalability and open-ended dynamics. Some examples are Cellular Automata (Von Neumann 1966), and their more recent counterparts such as Neural Cellular Automata (Mordvintsev et al 2020) and Lenia (Chan, 2019), reaction-diffusion systems (Turing 1992, Mordvintsev 2021), and particle systems (Reynolds 1987, Mordvintsev) . Examples from neuroevolution are indirect encodings of neural networks inspired from morphogenesis such as cellular encodings (Gruau 1992), HyperNEAT (Stanley et al 2009), Hypernetworks (Ha 2016), HyperNCA (Najarro et al 2022), Neural Developmental Programs (Najarro et al 2023, Nisioti et al 2024) and Hebbian learning, showing improved robustness and generalisation. Aside biological evolution, cultural evolution can also lead to open-ended systems, such as human culture, aspects of which have been captured by computational models of social dynamics, as with Schelling's model (Schelling, 1978), Spatial Social Dilemmas (Nowak and May, 1992) and, more recently, groups of Large Language Models (Nisioti el al, 2024).
Guiding self-organising systems through evolution is a long-standing and promising practise, yet the inherent complexity of the dynamics of these systems complicates their scaling to domains where gradient-based methods or simpler models excel (Risi 2021). If we view self-organising systems as genotype to phenotype mappings, we can leverage techniques developed in the evolutionary optimization community to understand how they alter evolutionary dynamics and guide them better.
This perspective is becoming increasingly important as evolutionary algorithms are now being employed at scale (Novikov et al 2025, Lange et al 2025, X. Qiu et al ). A closer look at systems such as AlphaEvolve reveals their implicit evo-devo character, with program search reminiscent of prior work in genetic programming exploiting developmental encodings (Koza et al, 1994) . However, little effort has been devoted to analysing them as genotype to phenotype mappings in terms of properties such as robustness, navigability, or developmental bias.
J. Abramson et al., "Accurate structure prediction of biomolecular interactions with AlphaFold 3," Nature, pp. 1–3, May 2024, doi: 10.1038/s41586-024-07487-w.
J. R. Koza, Genetic programming II: automatic discovery of reusable programs. Cambridge, MA, USA: MIT Press, 1994.
B. Georgiev, J. Gómez-Serrano, T. Tao, and A. Z. Wagner, “Mathematical exploration and discovery at scale,” Nov. 06, 2025, arXiv: arXiv:2511.02864. doi: 10.48550/arXiv.2511.02864.
A. Novikov et al., “AlphaEvolve: A coding agent for scientific and algorithmic discovery,” June 17, 2025, arXiv: arXiv:2506.13131. doi: 10.48550/arXiv.2506.13131.
X. Qiu et al., “Evolution Strategies at Scale: LLM Fine-Tuning Beyond Reinforcement Learning,” Sept. 29, 2025, arXiv: arXiv:2509.24372. doi: 10.48550/arXiv.2509.24372.
J. Su, D. V. Vargas, and S. Kouichi, "One pixel attack for fooling deep neural networks," IEEE Trans. Evol. Computat., vol. 23, no. 5, pp. 828–841, Oct. 2019, doi: 10.1109/TEVC.2019.2890858.
R. Lam et al., "GraphCast: Learning skillful medium-range global weather forecasting," Aug. 04, 2023, arXiv: arXiv:2212.12794. Accessed: May 31, 2024. Online. Available: http://arxiv.org/abs/2212.12794
R. T. Lange, Y. Imajuku, and E. Cetin, “ShinkaEvolve: Towards Open-Ended And Sample-Efficient Program Evolution,” Sept. 17, 2025, arXiv: arXiv:2509.19349. doi: 10.48550/arXiv.2509.19349.
A. Cully, J. Clune, D. Tarapore, and J.-B. Mouret, "Robots that can adapt like animals," Nature, vol. 521, no. 7553, pp. 503–507, May 2015, doi: 10.1038/nature14422.
F. Chollet, "On the Measure of Intelligence," Nov. 25, 2019, arXiv: arXiv:1911.01547. doi: 10.48550/arXiv.1911.01547.
E. Strubell, A. Ganesh, and A. McCallum, "Energy and Policy Considerations for Deep Learning in NLP," Jun. 05, 2019, arXiv: arXiv:1906.02243. doi: 10.48550/arXiv.1906.02243.
S. Camazine, J.-L. Deneubourg, N. R. Franks, J. Sneyd, G. Theraulaz, and E. Bonabeau, Self-Organisation in Biological Systems, vol. 38. Princeton University Press, 2001. doi: 10.2307/j.ctvzxx9tx.
A. Mordvintsev, E. Randazzo, and E. Niklasson, "Differentiable Programming of Reaction-Diffusion Patterns," Jun. 22, 2021, arXiv: arXiv:2107.06862. doi: 10.48550/arXiv.2107.06862.
A. M. Turing, "The chemical basis of morphogenesis," Bltn Mathcal Biology, vol. 52, no. 1, pp. 153–197, Jan. 1990, doi: 10.1007/BF02459572.
C. W. Reynolds, "Flocks, herds and schools: A distributed behavioral model," in Proceedings of the 14th annual conference on Computer graphics and interactive techniques, in SIGGRAPH '87. New York, NY, USA: Association for Computing Machinery, Aug. 1987, pp. 25–34. doi: 10.1145/37401.37406.
Alexander Mordvintsev. Self-Organizing Particle Swarm. https://znah.net/icra23/
B. W.-C. Chan, "Lenia - Biology of Artificial Life," ComplexSystems, vol. 28, no. 3, pp. 251–286, Oct. 2019, doi: 10.25088/ComplexSystems.28.3.251.
B. A. y Arcas et al., "Computational Life: How Well-formed, Self-replicating Programs Emerge from Simple Interaction," Aug. 02, 2024, arXiv: arXiv:2406.19108. doi: 10.48550/arXiv.2406.19108.
W. Fontana, "Algorithmic Chemistry: A model for functional self-organization."
C. Adami and C. T. Brown, "Evolutionary Learning in the 2D Artificial Life System 'Avida,'" May 16, 1994, arXiv: arXiv:adap-org/9405003. doi: 10.48550/arXiv.adap-org/9405003.
S. Rasmussen, C. Knudsen, R. Feldberg, and M. Hindsholm, "The coreworld: emergence and evolution of cooperative structures in a computational chemistry," in Emergent computation, Cambridge, MA, USA: MIT Press, 1991, pp. 111–134.
E. Najarro, S. Sudhakaran, and S. Risi, "Towards Self-Assembling Artificial Neural Networks through Neural Developmental Programs," Jul. 16, 2023, arXiv: arXiv:2307.08197. Accessed: Oct. 03, 2023. Online. Available: http://arxiv.org/abs/2307.08197
E. Nisioti, E. Plantec, M. Montero, J. Pedersen, and S. Risi, "Growing Artificial Neural Networks for Control: the Role of Neuronal Diversity," in Proceedings of the Genetic and Evolutionary Computation Conference Companion, Melbourne VIC Australia: ACM, Jul. 2024, pp. 175–178. doi: 10.1145/3638530.3654356.
T. C. Schelling, "Micromotives and macrobehavior", 1st ed. New York: Norton, 1978.
M. A. Nowak and R. M. May, "Evolutionary games and spatial chaos", Nature, vol. 359, no. 6398, pp. 826–829, Oct. 1992, doi: 10.1038/359826a0.
E. Nisioti, S. Risi, I. Momennejad, P.-Y. Oudeyer, and C. Moulin-Frier, "Collective Innovation in Groups of Large Language Models",in ALIFE 2024: Proceedings of the 2024 Artificial Life Conference, MIT Press, 2024. Accessed: Feb. 06, 2025. Online. Available: https://direct.mit.edu/isal/proceedings-abstract/isal2024/36/123452
Submission format
Full papers and extended abstracts:
- Full papers (8 pages + references): Must cover the ACM Open APC (see below for more information)
- Extended Abstracts (up to 4 pages): Are not eligible for APC - no fee paid by the authors for ACM Open Access. An Extended Abstract provides a summary of a work-in-progress, typically just enough for readers to understand the idea, scope, and potential impact. It often lacks full methodology, detailed results, or extensive references.
Important dates
- Submission opening: February 2, 2026
- Submission deadline:
March 27, 2026April 03, 2026 - Notification: April 24, 2026
- Camera-ready: May 5, 2026
- Author's mandatory registration: May 11, 2026
ACMs new Open Access publishing model for 2026 ACM Conferences
Starting January 1, 2026, ACM will fully transition to Open Access. All ACM publications, including those from ACM-sponsored conferences, will be 100% Open Access. Authors will have two primary options for publishing Open Access articles with ACM: the ACM Open institutional model or by paying Article Processing Charges (APCs). With over 2,600 institutions already part of ACM Open, the majority of ACM-sponsored conference papers will not require APCs from authors or conferences (currently, around 76%).
Authors from institutions not participating in ACM Open will need to pay an APC to publish their papers, unless they qualify for a financial waiver. To find out whether an APC applies to your article, please consult the list of participating institutions in ACM Open and review the APC Waivers and Discounts Policy. Keep in mind that waivers are rare and are granted based on specific criteria set by ACM.
Understanding that this change could present financial challenges, ACM has approved a temporary subsidy for 2026 to ease the transition and allow more time for institutions to join ACM Open. The subsidy will offer:
- $250 APC for ACM/SIG members
- $350 for non-members
This represents a 65% discount, funded directly by ACM. Authors are encouraged to help advocate for their institutions to join ACM Open during this transition period.
This temporary subsidized pricing will apply to all conferences scheduled for 2026.
Additionally, SIGEVO will provide an additional subsidy of $125 to papers accepted to GECCO 2026 (and only for 2026) that are subject to APCs. This will make the final amounts to be paid:
- $125 (USD) for SIGEVO members
- $225 (USD) for non-members
It is IMPORTANT to mention that both forms of subsidy (by ACM and by SIGVO) only apply to GECCO 2026. Moreover, it is still to be determined how the SIGEVO subsidy will be implemented, either directly to the APC or in other forms.
Finally, we note that APC charges apply to accepted Full Papers, but Abstracts (1-2 pages), Extended Abstracts (1-4 pages) and Tutorials ARE NOT APC Eligible; i.e., an APC will not have to be paid for these types of contributions.
ACM Authorship and Peer Review Policies on Generative AI
GECCO follows the official ACM policies on authorship and peer review, including the use of generative AI tools.
Under ACM's Authorship policy, generative AI tools and technologies cannot be listed as authors of an ACM published Work. The use of generative AI tools and technologies for assistance must be fully disclosed in the manuscript's Acknowledgments section. Authors are fully accountable for the originality, accuracy, and integrity of all submitted material.
In accordance with ACM's Peer Review policy, reviewers must not upload or share submitted manuscripts or review materials with generative AI systems. Reviewers may use generative AI or tools with the sole purpose of improving the quality and readability of reviewer reports for the author.
ACM is actively developing tools to help identify improper AI use in submissions, and GECCO may employ available detection methods. Submissions found to violate ACM policies may be rejected.
-
Organizers
Ettore Randazzo is a Senior Software Engineer and Researcher at Google Research in Zürich, Switzerland. Prior to this he was a Research Assistant at the University of Illinois at Chicago where he acquired a Master’s degree in Computer Engineering. His interests include machine intelligence, complex artificial life, philosophy, ethics, logic and mathematics, gaming, music (including playing electric guitar and piano), and writing.
Eyvind Niklasson is an AI Resident at Google Research in Zürich, Switzerland, where he among other topics conducts research in Neural Cellular Automatas and self-replicating programs. He has previously worked as a data scientist at Gro Intelligence developing unsupervised learning models. Before that, Eyvind worked as a research assistant at Cornell University attached to the Cornell High Energy Synchrotron Source.