Volume 17, Issue 2

Newsletter of the ACM Special Interest Group on Genetic and Evolutionary Computation


Welcome to the second 2024 (Summer) issue of the SIGEvolution newsletter! Our intriguing cover image features a Portuguese coin immediately after minting, created using Evolutionary Computation and themed around the “Digital World” (photo by Nuno Silva / INCM. 2023). An article describing this coin’s co-creation, from conceptualisation to production, opens this issue. We continue with a personal account of this year’s EvoStar conference from an engaged and energetic PhD student. We also feature a recent PhD dissertation entitled “Evolutionary Computation Methods for Instance Generation in Optimisation Domains”.

We conclude with the usual announcements, forthcoming events and calls for submissions. Remember to get in touch if you’d like to contribute or have suggestions for future newsletter issues.

Gabriela Ochoa (Editor)

Designing Coins with Evolutionary Computation

Penousal Machado, Tiago Martins, João Correia, Luís Espírito Santo*, Nuno Lourenço, João Cunha, Sérgio Rebelo, Pedro Martins, João Bicker

University of Coimbra, CISUC/LASI, DEI, Coimbra, Portugal
* also with Vrije Universiteit Brussel, Brussels, Belgium

{machado, tiagofm, jncor, lesanto, naml, jmacunha, srebelo, pjmm, bicker}@dei.uc.p


In recent years, the application of Artificial Intelligence (AI) for creative and artistic endeavours has attracted considerable attention, increasing the opportunities to use AI for many art and design tasks. This paper describes our response to a unique challenge presented by the Portuguese National Press-Mint (INCM): to use AI to design a commemorative coin that celebrates the “digital world”. We explain the process of this coin’s co-creation, from conceptualisation to production, highlighting the design process, key obstacles encountered, and technical innovations made to meet the challenge. These include developing an evolutionary art system guided by Contrastive Language-Image Pre-training (CLIP) and Machine Learning (ML)-based aesthetic models, a system for prompt evolution, and a representation for encoding genotypes in mintable format. This collaboration produced a limited edition 10 euro silver proof coin (Figure 1), with a total of 4,000 units minted by the National Press-Mint. The coin was met with enthusiasm, selling out within two months. This work contributes to Computational Creativity (CC), particularly co-creativity, co-design, and digital art, and represents a significant step in using AI for Numismatics.

Figure 1: Reverse (left) and obverse (right) of the coin “Digital World”. Photos by Nuno Silva / INCM.

This project began with the question: Can you create a coin themed around the digital world using AI? Our goal was to create a coin representing AI’s interpretation of the digital world, aligning with both INCM’s collection and our lab’s values.

Design Brief and Implications

Coins are uniquely positioned as both legal tender and cultural icons, differing from medals through their dual role as currency and art. While anyone can mint a medal, only the government can mint a coin, which holds monetary value and facilitates transactions. Designing coins involves balancing functionality and aesthetics, considering factors like mintability, durability, recognisability, legal requirements, thematic relevance, and visual appeal.

Our goal was to create a coin that pays tribute to the rich tradition of numismatics and the National Press-Mint, while also reflecting our identity as an AI and Design Lab., and our commitment to human-centred AI. This vision resulted in three primary design principles:

  1. The coin should embody AI’s interpretation of a coin themed around the “digital world”.
  2. One face of the coin is crafted by AI for humans, while the other is designed by humans for AI.
  3. Both sides should express the same concept, with each side’s design tailored to its target audience.

Initial experiments with off-the-shelf generative AI tools like Stable Diffusion and DALL-E produced unsatisfactory results. The images were cliched and did not align with our vision (see Figure 2).

Figure 2: Examples of coins themed around the digital world created with off-the-shelf generative AI models.

We recognised that it is not just any coin; it is a coin that will belong to the collection of INCM. Similarly, it cannot be designed by just any AI; it must be an AI we developed, aligned with our values and vision. These insights led to two additional design guidelines:

  1. The AI must align with our views. It is our lab’s next project and must fit our ethos.
  2. The AI must align with the INCM collection. It is the next coin in the series and must fit seamlessly.

Generating Coins Themed Around the Digital World

The novelty of our work lies in the AI tools developed during this project, namely a new Evolutionary Computation (EC) engine that takes advantage of the semantic interpretation capabilities of CLIP [8], ML aesthetic models, and an EC system for evolutionary prompt design; and the application of these to the historically and culturally rich field of numismatics.

Evolving Coin Heightmaps

We adopt an expression-based evolutionary art approach popularised by Sims [10], using pyNEvAr (https://github.com/cdvetal), a recent version of NEvAr [3, 4], implemented with TensorGP [1]. Each individual’s genotype is a mathematical expression, and the genotype-to-phenotype mapping involves evaluating these expressions to generate images. This is done by calculating the output of the expression for every pixel in the image space, with the expression’s variables x and y corresponding to the pixel’s coordinates, and the expression’s output determining the pixel’s colour.

Each individual’s genotype is a mathematical expression, and the genotype-to-phenotype mapping involves evaluating these expressions to generate images. Since the coin is circular, we use polar coordinates. The output is produced by calculating the expression’s output for every pixel of the im-
age. The images are interpreted as heightmaps, creating the 3D surface of one of the faces of the coin (see Figure 3).

Figure 3: Examples of genotype-phenotype pairs.

Our evolutionary engine also communicates with CLIP and publicly available aesthetic models. We specify a text prompt, such as “a coin themed around the digital world”, and use CLIP to convert this prompt into a text feature vector. CLIP extracts the corresponding image feature vector for each generated image, allowing us to assign fitness based on cosine similarity between the text feature vector and each image feature vector.

A key difference between our system and popular generative AI tools is that our generator is not data-driven. It has never seen paintings or used human design primitives. It focuses on innovation, not imitation.

While a prompt like “a coin-themed around the digital world” can work, the resulting images are often mediocre. Moreover, our system aims to produce a coin that fits INCM’s collection and aligns with our group’s work. Using prompts may help to ensure these contexts are considered when assigning fitness.

For that purpose, we began by creating an image database composed of 910 contemporary INCM coins and selected 34 with the help of INCM experts. Using CLIP interrogator [7], we extracted roughly 400 expressions from these coins and curated them to remove content-related ones (e.g., flower, ship, horse).

We applied the same process using pyNEvAr. We curated high-quality images evolved with user-guided and automated fitness assignment. In the automated approach, fitness is assigned to maximise the aesthetic score of LAION-5B [9]. CLIP interrogator extracted several unexpected yet understandable expressions that appear to enhance image quality (e.g. “top view, “circular object”, “uncompressed png”). We eliminated all expressions related to specific styles (e.g., “in the style of Escher”) and content (e.g., “eyes”).

MetaPrompter [5], a prompt evolution system developed specifically for this project, was used to evolve prompts that, by incorporating some of the above expressions, promote the alignment of the images with the design guidelines 1, 4 and 5. An example of a high-quality evolved prompt follows: “black
and white image, an image of the internet, inspired by Ai Wei-wei, society, in the style of art nouveau, Behance contest winner, simulacra and simulation, top-view.”

Experimental Results

We conducted several evolutionary runs using the evolved prompts, performing 30 independent runs for each of the 14 selected prompts, totalling 420 runs and evolving roughly 43 million images. A process of automatic curatorship, inspired by the work of Correia et al. [2], reduced this number to 1974 images, further narrowed to 142 through visual inspection. These images were 3D rendered, and a blind vote by our team led to a selection of 24 images. The creative director of our lab selected three, and the team unanimously picked one. Figure 4 presents the genotype of the selected individual and a link to a video that illustrates how the different subtrees contribute to the final result.

Figure 4: Visualisation of the expression that generates the coin’s reverse face. The expression tree rendering is available at: https://cdv.dei.uc.pt/2024/coin-expression-visualisation.mp4

The prompt used to generate the selected image is: “black and white image, an image of a broadcasting world, inspired by Alvar Aalto, in the style of art nouveau, in the style of figurativism, abstract, top-view”. The analysis of this prompt shows that “Alvar Aalto” is a keyword from INCM coins, linked to a coin by Eduardo Souto de Moura honouring Siza Vieira (both are Pritzker Prize-winning architects), and Aalto significantly influenced Vieira. Though the CLIP interrogator did not identify Moura and Vieira, Aalto’s name contributed to the architectural nature of the design.

By Humans for AI: Code Representation

The coin’s obverse face (Figure 5, right) is a graphical representation of the genetic code of the reverse image (Figure 5, left). To achieve this, we developed a system that converts the genotypes evolved by AI into a visual composition of concentric arcs, encoding the mathematical expression corresponding to the reverse image. This system uses a dictionary-based compression algorithm to encode the sequence of functions and values that constitute the genotype. Continuous arcs represent mathematical functions, while interrupted arcs represent numerical values. Inspired by data storage disks, this arc-based system is designed to be machine-readable, providing access to the instructions needed to reproduce the reverse image. Surrounding the genotype representation, we added graphic elements and typography required for official currency. The typography was specifically generated for the coin using the parametric system LetterSpecies [6].

Figure 5: Reverse (left) and obverse (right) faces of the coin “Digital World.” Photos by Nuno Silva / INCM.


The use of AI in creative and artistic contexts has garnered significant interest. Following this trend, INCM invited us to use AI to aid in designing a commemorative coin themed around the “digital world”. Designing coins requires balancing practical functions and aesthetic qualities, considering factors such as mintability, durability, recognizability, legal requirements, thematic significance, and visual appeal.

Our goal with this project was to create a coin that honours the traditions of numismatics and the Portuguese National Press-Mint, while also reflecting the identity of our AI and Design Lab and our perspectives on CC research. We aimed to symbolise the “digital world” and explore how co-creativity can enhance traditional numismatic art, bridging the gap between coin minting heritage and computational aesthetics. Additionally, the coin also references how humans and machines are increasingly inseparable, literally two faces of the same coin. It illustrates Evolutionary Computation may promote human-machine cooperation and expand human creative potential, fostering ethical use that transcends mere imitation of human artistry.


The authors would like to express their gratitude to Imprensa Nacional–Casa da Moeda for presenting us with the challenge that originated this research. Part of this work was developed during Penousal Machado’s sabbatical stay at the BEACON Center for the Study of Evolution in Action at Michigan State University. We would like to thank Wolfgang Banzhaf, BEA-CON, and MSU for hosting and supporting this endeavour. Special thanks to Fabio Gouveia for his crucial role in generating the digital assets. This work is funded by the FCT – Foundation for Science and Technology, I.P./MCTES through national funds (PIDDAC), within the scope of CISUC R&D Unit – UIDB/00326/2020 or project code UIDP/00326/2020


[1] Francisco Baeta, Joao Correia, Tiago Martins, and Penousal Machado. TensorGP – genetic programming engine in TensorFlow. In EvoApplications, volume 12694 of Lecture Notes in Computer Science, pages 763–778. Springer, 2021.

[2] João Correia, Penousal Machado, Juan Romero, Pedro Martins, and F. Amilcar Cardoso. Breaking the mould: an evolutionary quest for innovation through style change. In Computational Creativity, pages 353– 398. Springer, 2019.

[3] Penousal Machado and Amilcar Cardoso. All the truth about NEvAr. Appl. Intell., 16(2):101–118, 2002.

[4] Penousal Machado, Juan Romero, and Bill Z. Manaris. Experiments in computational aesthetics. In The Art of Artificial Evolution, Natural Computing Series, pages 381–415. Springer, 2008.

[5] Tiago Martins, João Miguel Cunha, João Correia, and Penousal Machado. Towards the evolution of prompts with metaprompter. In EvoMUSART@EvoStar, volume 13988 of Lecture Notes in Computer Science, pages 180–195. Springer, 2023.

[6] Fabio Andre Pereira, Tiago Martins, Sergio Rebelo, and João Bicker. Generative type design: Creating glyphs from typographical skeletons. In ARTECH, pages 19:1– 19:8. ACM, 2019.

[7] pharmapsychotic. CLIP interrogator: Image to prompt with BLIP and CLIP. https://github.com/ pharmapsychotic/clip-interrogator, 2023. Accessed: 2023-09-01.

[8] Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, and Ilya Sutskever. Learning transferable visual models from natural language supervision. In ICML, volume 139 of Proceedings of Machine Learning Research, pages 8748–8763. PMLR, 2021.

[9]  Christoph Schuhmann, Romain Beaumont, Richard Vencu, Cade Gordon, Ross Wightman, Mehdi Cherti, Theo Coombes, Aarush Katta, Clayton Mullis, Mitchell Wortsman, Patrick Schramowski, Srivatsa Kundurthy, Katherine Crowson, Ludwig Schmidt, Robert Kaczmar- czyk, and Jenia Jitsev. LAION-5B: an open large-scale dataset for training next generation image-text models. In NeurIPS, 2022.

[10]  Karl Sims. Artificial evolution for computer graphics. In SIGGRAPH, pages 319–328. ACM, 1991.

Summary of EvoStar 2024

Jessica Mégane, University of Coimbra

This year’s EvoStar conference was held from April 3rd to 5th in the beautiful town of Aberystwyth, a place as delightful to visit as it is challenging to pronounce!

Although it takes a few hours to get to the town from the airport, the train ride is quite beautiful, offering stunning views of the countryside and plenty of sheep to count if you need a nap. Before digging details of the conference, I must congratulate Christine Zarges and the organizing team for putting together such a fantastic event.

For us students, the conference starts the evening before. Although the day began clear and bright, it unfortunately started raining just as the Student Reception was about to kick off. This event provides students with a variety of activities to get to know each other.

One of the highlights of the student reception is the EvoStar quiz against the “Old Crocs,” who triumphed again this year. The evening concluded with the EvoChoir practising their songs in preparation for the conference dinner. It was a delight for returning students, while new attendees looked on with a mix of amusement and confusion, wondering what they had got themselves into. The day ended with the students having dinner in town.

After a long walk uphill to the university (or by public transport for the less adventurous), the conference officially started with Penousal Machado, the SPECIES president, opening the event. The day truly kicked off with an inspiring plenary talk by Jon Timmis, entitled “Evolution, Immunity, and Robots: An Interdisciplinary Adventure“.

Jon’s insightful presentation showcased his journey into the intersection of evolutionary, immunologic, and robotics fields. He detailed the challenges of starting in such a multidisciplinary realm but also highlighted the cool results he’s achieving. From using robots for fault diagnosis to creating robots capable of autonomous evolution and design, his work represents a fascinating blend of innovation and problem-solving.

The day concluded with the Poster Session, a vibrant gathering where everyone shared their work and received insightful comments and questions. As always, we saw many creative posters, and this year was particularly notable for the live demos, especially from the EvoMUSART track, adding an extra layer of innovation and interactivity to the conference.

EvoStar’s Poster Session.

On the second day, the first session of EvoCOP kicked off, while EvoAPPS continued with two morning sessions. Following the first coffee break, we eagerly gathered for the Julian Francis Miller Award session. This year’s deserving recipients, Hod Lipson and Dario Floreano were honoured, although Hod Lipson couldn’t join us in person. Nonetheless, we had an enlightening morning with them, discussing a range of intriguing topics.

During the conversation, the importance of integrating physical embodiment alongside software advancements in AI was emphasized. Two main themes emerged: overcoming the reality gap and sustainability. Various strategies were discussed, and if you’re curious, I highly encourage you to watch the plenary talks as they are available on YouTube!

After this session, the students rushed for the Student Workshop, featuring: Conor Ryan, Bing Xue, Colin Johnson, Emma Hart, and Ernesto Costa. The workshop provided a unique opportunity for students to gain insights from these experts in the field, covering topics from the inception of their PhDs to the challenges they faced and overcame.

Student Workshop

The students gained a profound understanding of diverse academic paths and challenges across generations, countries, and genders. The afternoon proceeded with sessions from all conferences, featuring EvoAPPS and EvoCOP Best Paper nominations.

The conference dinner, held at the University, kicked off with drinks next to the EvoStar exhibition, “Computational Intelligence in Art and Design,” which showcased curated works exploring the evolution of computational approaches in creative contexts. Somehow, we also managed to squeeze everyone together for a group picture.

Group Photo.

The highlight of the evening was Mario Giacobini receiving the Outstanding Contribution award. Despite his absence, Mario graciously accepted the award via video call, reminding us all that his spirit was still very much present (albeit pixelated).

Conference Dinner.

And of course, what is a conference dinner without the EvoChoir serenading us with their classics? From “Bella Ciao” to “Amigos para Siempre,” ending with a heart-warming attempt of “All my Loving,” they had us singing along in no time.

Now, as a Portuguese, I couldn’t let this moment pass without a bit of national pride. You see, while the Italians, Spanish, and English have their songs in the EvoChoir repertoire, we Portuguese have been feeling a bit left out. So, in a bold move to remedy this situation, we proudly belted out “Grândola, Vila Morena,” leaving everyone wondering if they’d accidentally stumbled into a Portuguese karaoke night.

The final day started with concurrent sessions of EvoMUSART, EvoCOP and EML, marking the culmination of the conference. After the much-needed coffee break, attendees gathered for the anticipated plenary talk by Sabine Hauert, titled “Evolving Swarms Across Scales: From Nanomedicine to City Logistics.” Sabine’s presentation proved to be captivating, leaving the audience buzzing with ideas of how swarms can assist in real-life scenarios such as in logistics and medicine through their efficiency, scalability, and robustness. She emphasized the importance of interpretable controllers to enhance transparency and trust in these systems.
Lastly, it was the closing session, where the much-anticipated awards were presented. Among the tough competition, the deserving winners emerged as follows:

  • EvoAPPS: “Evolving Feature Extraction Models for Melanoma Detection: A Co-operative Co-evolution Approach”, Taran Cyriac John, Qurrat Ul Ain, Harith Al-Sahaf and Mengjie Zhang
  • EvoCOP: “A Neural Network Based Guidance for a BRKGA: An Application to the Longest Common Square Subsequence Problem”, Jaume Reixach, Christian Blum, Marko Djukanovic and Günther R. Raidl
  • EuroGP: “Naturally Interpretable Control Policies via Graph-based Genetic Programming”, Giorgia Nadizar, Eric Medvet and Dennis G. Wilson
  • EvoMUSART: “Collaborative Interactive Evolution of Art in the Latent Space of Deep Generative Models”, Ole Hall and Anil Yaman

After all the awards were given, including Best Poster, Best Student Paper, Outstanding Students, Dissemination, and The Great EvoStar Scavenger Hunt, attendees headed to lunch. With the awards ceremony marking the official closure of the conference, some participants opted to extend their stay and embarked on a social trip to explore the city further.

National Library of Wales (Aberystwyth).

For those who had to leave, all goodbyes were exchanged, with hopeful anticipation to join the conference next year (which, if you don’t remember from the conference closing ceremony, will be held in Trieste, Italy). Until then, best wishes to all! Hopefully, we will see each other there!

About the Author

Jessica Mégane is a PhD student at the bio-inspired Artificial Intelligence lab of the Center of Informatics and Systems of the University of Coimbra, Portugal. Her research focuses on probabilistic grammar-based genetic programming algorithms.

PhD Thesis: Evolutionary Computation Methods for Instance Generation in Optimisation Domains

Alejandro Marrero, Departamento de Ingenieria Informatica y de Sistemas, Universidad de La Laguna (ULL) amarrerd@ull.edu.es

Supervisors: Prof. Eduardo Segredo and Prof. Coromoto León

The generation of instances of optimisation problems is a very common task in Computer Science. Traditionally, researchers apply statistical or pseudo-random methods to create instances used to validate their proposals: algorithms or operators. At the same time, some authors have proposed sets known as benchmarks so that new proposals can be evaluated in these instances, thus avoiding the task of generating instances. However, these sets are often characterised by (1) being designed to be hard to solve by off-the-shelf, state-of-the-art algorithms at the time of their creation and (2) by their low diversity, meaning the instances tend to share many similar characteristics.

Figure1: Hiking Planning (Knapsack) Problem.

Hence, there is a need for instances that exhibit some diversity in their features so that the strengths and weaknesses of a wider range of solvers can be evaluated. This factor is essential in problems such as Algorithm Selection; i.e., mapping a portfolio of algorithms to a set of instances based on their performance. Since, in practice, there is no algorithm that can be expected to outperform others in every instance, collecting diverse instances with known best solvers could facilitate the evaluation of the strengths and weaknesses of the algorithms. Generating instances that are diverse from one another requires a method that (1) is capable of performing a space exploration and (2) has a mechanism for measuring diversity with respect to the rest of the instances encountered earlier in the search.

This thesis examines the problem of generating diverse and performance-biased instances from a portfolio of algorithms by proposing two major variants of Novelty Search (NS). The methods apply single and multi-objective approaches to generate instances that are diverse and discriminatory, meaning they are designed to be diverse among themselves and also easy to solve for one target algorithm and not for others in a predefined portfolio. Although the proposals are mainly evaluated using the well-known Knapsack Problem (KP) (Fig. 1) and Travelling Salesman Problem (TSP), current research shows that the methods can be generalised to other domains of combinatorial optimisation such as Bin-Packing (BP). The results from the experimental assessment suggest that both NS methods are able to generate diverse and discriminatory instances in both domains when using a portfolio of deterministic heuristics. Moreover, our methods outperformed previous Evolutionary Algorithm (EA) and even state-of-the-art approaches in the KP domain.

Finally, the methods are integrated into DIGNEA, a Diverse Instance Generator with Novelty Search and Evolutionary Algorithms, a ready-to-use framework available in two languages: C++ and Python. The frameworks were developed during the research associated to this thesis to facilitate the generation of diverse and discriminatory instances for optimisation domains for the research community. Both versions are available for the public in a GitHub repository, a Docker image for containerized runs of the C++ version and as a Python package that can be installed via pip.
The full dissertation can be accessed from the ULL official repository.

Related Publications

Journal Articles

  • Marrero, A., Segredo, E., León, C. and Hart, E. 2024. Synthesising Diverse and Discriminatory Sets of Instances using Novelty Search in Combinatorial Domains. Evolutionary Computation.
  • Marrero, A., Segredo, E., León, C. and Hart, E. 2023. DIGNEA: A Tool to Generate Diverse and Discriminatory Instance Suites for Optimisation Domains. SoftwareX 22.
  • Marrero, A., Segredo, E., León, C. and Segura, C. 2020. A Memetic Decomposition- Based Multi-Objective Evolutionary Algorithm Applied to a Constrained Menu Planning Problem. Mathematics 8, 1-18.

Conference Articles

  • Marrero, A., Segredo, E., León, C., and Hart, E. 2024. Learning Descriptors for Novelty-Search Based Instance Generation via Meta-evolution. In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO ’24). Association for Computing Machinery, New York, NY, USA, 312–320.
  • Marrero, A., Segredo, E., Hart, E., Bossek, J., and Neumann, A. 2023. Generating diverse and discriminatory knapsack instances by searching for novelty in variable dimensions of feature-space. In Proceedings of the Genetic and Evolutionary Com- putation Conference (GECCO ’23). Association for Computing Machinery, New York, NY, USA, 312–320.
  • Marrero, A., Segredo, E., León, C., and Hart, E. 2022. A Novelty-Search Approach to Filling an Instance-Space with Diverse and Discriminatory Instances for the Knapsack Problem. In Parallel Problem Solving from Nature – PPSN XVII: 17th International Conference, PPSN 2022, Dortmund, Germany, September 10–14, 2022, Proceedings, Part I. Springer-Verlag, Berlin, Heidelberg, 223–236.
  • Marrero, A., Segredo, E., and León, C. 2021. A parallel genetic algorithm to speed up the resolution of the algorithm selection problem. In Proceedings of the Genetic and Evolutionary Computation Conference Companion (GECCO ’21). Association for Computing Machinery, New York, NY, USA, 1978–1981.
  • Marrero, A., Segredo, E., and León, C. 2019. On the automatic planning of healthy and balanced menus. In Proceedings of the Genetic and Evolutionary Computation Conference Companion (GECCO ’19). Association for Computing Machinery, New York, NY, USA, 71–72.

About the Author

Alejandro Marrero completed his Bachelor’s degree in Computer Science in 2017. That same year, he began his Master’s studies in Computer Science at the University of La Laguna. During the 2018-2019 academic year, he finished his Master’s in Computer Science, receiving the Extraordinary Award for the best academic record in the Master’s program. Additionally, in 2018 he joined the Parallel Algorithms and Languages (PAL) research group at ULL as a PhD student. Starting from the 2019 academic year, he was awarded an FPI grant by the Canary Island government, which allowed him to develop his doctoral thesis “Evolutionary Computation Methods for Instance Generation in Optimization Domains.”

He earned his Doctorate with the highest honours, “Sobresaliente Cum Laude,” and an international mention. Moreover, he has collaborated on several local research projects within the PAL group. As a result of his research, he has produced nine publications in high-impact international conferences and journals, mainly focused on the application of evolutionary and Machine Learning techniques to the resolution of optimisation problems and the generation of instances of combinatorial problems.


SPECIES Society offers up to three scholarships for current research students and recent PhD graduates in its areas of interest. The scholarships will involve an in-person internship of three months in one of the host institutions, working under the supervision of an advisor

The program offers the chance to collaborate with a new research group, providing fresh perspectives and fostering innovation. Participants will also experience the life and culture of the host country, and have the opportunity to network with leading experts in the field.

Selected candidates will receive a monthly allowance of 900 euros to cover accommodation, living expenses, and other costs. Additionally, if a paper resulting from the scholarship is accepted, the registration fee for EvoStar will be waived. 

The application deadline is July 10, 2024 (AoE).

For more details, including a list of available host institutions and feedback from previous editions, visit the SPECIES website or send an email to students@species-society.org

The SPECIES Summer School is looking for up to 24 students interested in gaining evolutionary computation and general research work skills, networking with the school mentors and with other students and enjoying fun activities and a nice stay by the Mediterranean!

We combine tutorials, in which the students learn the theory from experts, with hands-on challenges, in which the students work together in a research project. Not to mention the outdoor and beach activities! 

Mentors for 2024

  • Aniko Ekart — Aston University, UK
  • Tea Tušar — Josef Stefan Institute, Slovenia
  • Eric Medvet — University of Trieste, Italy
  • Jose Ignacio Hidalgo — Universidad Complutense de Madrid, Spain

Dates: August 26th (Monday) to September 1st (Sunday) 2024.

Venue: Beautiful beach resort in Moraira,  Spain La Marina Youth Hostel (less than two hours from Valencia)

ACM Transactions on Evolutionary Learning and Optimization (TELO)

Current Issue: Volume 4, Issue 2June 2024

Special Issue on the Best of GECCO 2022: Part II


Table of Content

  • Introduction to the “Best of GECCO 2022” Special Issue: Part II. Jonathan Fieldsend, Markus Wagner. Article No.: 6, Pages 1–2. https://doi.org/10.1145/3665797
  • Iterated Local Search with Linkage Learning. Renato Tinós, Michal W. Przewozniczek, Darrell Whitley, Francisco Chicano. Article No.: 7, Pages 1–29. https://doi.org/10.1145/3651165
  • Multiobjective Evolutionary Component Effect on Algorithm Behaviour. Yuri Lavinas, Marcelo Ladeira, Gabriela Ochoa, Claus Aranha. Article No.: 8, Pages 1–24. https://doi.org/10.1145/3612933
  • Generating Cheap Representative Functions for Expensive Automotive Crashworthiness Optimization. Fu Xing Long, Bas van Stein, Moritz Frenzel, Peter Krause, Markus Gitterle. Article No.: 9, Pages 1–26. https://doi.org/10.1145/3646554
  • Marginal Probability-Based Integer Handling for CMA-ES Tackling Single- and Multi-Objective Mixed-Integer Black-Box Optimization. Ryoki Hamano, Shota Saito, Masahiro Nomura, Shinichi Shirakawa. Article No.: 10, Pages 1–26. https://doi.org/10.1145/3632962
  • The Influence of Noise on Multi-parent Crossover for an Island Model Genetic Algorithm. Brahim Aboutaib, Andrew M. Sutton. Article No.: 11, Pages 1–28. https://doi.org/10.1145/3630638
  • On the Use of Quality Diversity Algorithms for the Travelling Thief Problem. Adel Nikfarjam, Aneta Neumann, Frank Neumann. Article No.: 12, Pages 1–22. https://doi.org/10.1145/3641109

Call for Papers

ACM Transactions on Evolutionary Learning and Optimization (TELO)

Special Issue on Integrating Evolutionary Algorithms and Large Language Models

Guest Editors

  • Erik Hemberg, Massachusetts Institute of Technology, USA, hembergerik@csail.mit.edu
  • Una-May O’Reilly, Massachusetts Institute of Technology, USA, unamay@csail.mit.edu
  • Dennis Wilson, ISAE-Supaero, University of Toulouse, France, dennis.wilson@isae.fr

We invite research that investigates how Evolutionary Algorithms and Large Language Models can be combined to yield new insights, results, and questions in Evolutionary Computation. We are interested in a wide range of integrations, including LLM-assisted evolution, LLMs for search operators, multi-objective and open-ended optimization using LLMs, andanalysis on search spaces, robustness, and benchmarks.

Important Dates

  • Open for Submissions: June 1, 2024
  •  Submissions deadline: October 1, 2024
  •  First-round review decisions: January 1, 2025
  •  Deadline for revision submissions: March 1, 2025
  •  Notification of final decisions: June 1, 2025

Submission Information

Submission Information Manuscripts should be prepared according to the “Guidelines for Authors” section at https://dl.acm.org/journal/telo/author-guidelines and submissions should be made through the journal submission website at https://mc.manuscriptcentral.com/telo  by selecting the Manuscript Type “Special Issue on Integrating Evolutionary Algorithms and Large Language Models”. If you would like to apply for an ACM Reproducibility Badge, please clearly state this in your Cover Letter.

Forthcoming Events

GECCO 2024 Melbourne (hybrid), July 14 – 18, 2024

The Genetic and Evolutionary Computation Conference (GECCO) presents the latest high-quality results in genetic and evolutionary computation since 1999. Topics include: genetic algorithms, genetic programming, swarm intelligence, complex systems, evolutionary combinatorial optimization and metaheuristics, evolutionary machine learning, learning for evolutionary computation, evolutionary multiobjective optimization, evolutionary numerical optimization, neuroevolution, real world applications, search-based software engineering, theory, benchmarking, reproducibility, hybrids and more.

PPSN 2024 September 14 – 18, 2024
Hagenberg, Austria

The International Conference on Parallel Problem Solving From Nature is a biannual open forum fostering the study of natural models, iterative optimization heuristics search heuristics, machine learning, and other artificial intelligence approaches. We invite researchers and practitioners to present their work, ranging from rigorously derived mathematical results to carefully crafted empirical studies.

About this Newsletter

SIGEVOlution is the newsletter of SIGEVO, the ACM Special Interest Group on Genetic and Evolutionary Computation. To join SIGEVO, please follow this link: [WWW].
We solicit contributions in the following categories:

Art: Are you working with Evolutionary Art? We are always looking for nice evolutionary art for the cover page of the newsletter.

Short surveys and position papers. We invite short surveys and position papers in EC and EC-related areas. We are also interested in applications of EC technologies that have solved interesting and important problems.

Software. Are you a developer of a piece of EC software, and wish to tell us about it? Then send us a short summary or a short tutorial of your software.

Lost Gems. Did you read an interesting EC paper that, in your opinion, did not receive enough attention or should be rediscovered? Then send us a page about it.

Dissertations. We invite short summaries, around a page, of theses in EC-related areas that have been recently discussed and are available online.

Meetings Reports. Did you participate in an interesting EC-related event? Would you be willing to tell us about it? Then send us a summary of the event.

Forthcoming Events. If you have an EC event you wish to announce, this is the place.

News and Announcements. Is there anything you wish to announce, such as an employment vacancy? This is the place.

Letters. If you want to ask or say something to SIGEVO members, please write us a letter!

Suggestions. If you have a suggestion about how to improve the newsletter, please send us an email.

Contributions will be reviewed by members of the newsletter board. We accept contributions in plain text, MS Word, or Latex, but do not forget to send your sources and images.

Enquiries about submissions and contributions can be emailed to gabriela.ochoa@stir.ac.uk
All the issues of SIGEVOlution are also available online at: evolution.sigevo.org

Notice to contributing authors to SIG newsletters
As a contributing author, you retain the copyright to your article. ACM will refer all requests for republication directly to you.

By submitting your article for distribution in any newsletter of the ACM Special Interest Groups listed below, you hereby grant to ACM the following non-exclusive, perpetual, worldwide rights:

  • to publish your work online or in print on the condition of acceptance by the editor
  • to include the article in the ACM Digital Library and in any Digital Library-related services
  • to allow users to make a personal copy of the article for noncommercial, educational, or research purposes
  • to upload your video and other supplemental material to the ACM Digital Library, the ACM YouTube channel, and the SIG newsletter site

If third-party materials were used in your published work, supplemental material, or video, make sure that you have the necessary permissions to use those third-party materials in your work

Editor: Gabriela Ochoa

Sub-editor: James McDermott

Associate Editors: Emma Hart, Bill Langdon, Una-May O’Reilly, Nadarajen Veerapen, and Darrell Whitley