Call For Papers: Special Issue on the Emergence of Modularity and Self-Organization

 

AIMS AND SCOPE

Springer Link here

Modularity is a concept that is intuitively clear, yet it can be conceptually difficult to pin down because it appears in a multitude of forms in nature and technology. Thus, support for modularity is a central element in human attempts to build complex systems in general. Software would not scale without functions and objects, likewise electronic circuits and mechanical systems can only be constructed through extensive reuse of modules at different levels of selection. Viewed from this perspective, modules take the form of a `process view' in which the operation performed by each component remains consistent while the overall system complexity increases.

However, this need not be the only approach to defining modules. From a biological perspective, a structural view might imply that modules are components of a system with stronger connections, or components defined by more frequent (internal) interaction. Both process and structural views implicitly attempt to define modules in terms of the degree of autonomy versus integration. Another potentially important aspect of a module is how it contributes to the dynamics of the wider system's behaviour, and how its contribution may change over time. Moreover, modules might invoke other modules, or sequences of modules may be invoked depending on context, facilitating the interpretation of behaviours at steadily higher levels of abstraction. 

This special issue invites new perspectives on the role of modularity in addressing issues such as scalability, reuse, and co-design in evolvable machines. We are particularly interested in submissions that illustrate advances to: 

• Open ended development of hierarchical relationships between modules and/or 
• Modular self-organization and emergence to achieve specific functional properties and/or
• Biological underpinnings of modularity in digital evolution of computer programs/evolvable machines.

We invite authors to submit works that illustrate the impact of modularity and self-organization on the ability to discover genotype/phenotypes more efficiently or improve the efficiency of operation. To this end, ongoing themes include mechanisms by which communication, ensembles, and cellular automata enable modules to develop or interact. Another related topic is the role of modularity on improving interpretability, where specific decision-making processes might be associated with particular modules.

Environments that demonstrate the importance of modularity are also of interest and might include multi-task learning or situations in which catastrophic forgetting plays a role. 

We also invite submissions that illustrate how co-design or co-evolution may result in better use of modules, or to what degree decomposing a task facilitates the organization of behavioural properties through module reuse.

TOPICS OF INTEREST

Impact of modularity and self organization on:

• efficiency of operation
• compartmentalizing credit assignment such that only specific modules are refined / catastrophic forgetting is mitigated
• emergence of individual versus group behaviours and their co-ordination
• hierarchical relationships versus ensembles or teams, and major transitions
• generalization, robustness, and evolvability
• automatic feature selection, feature construction and/or interpretability
• hardware acceleration, microarchitectures, and cyber-physical systems

Role of task transfer, multi-task, or continuous learning on:

• self organization, complexity, and emergence of modularity
• organization and development of units of selection
• the co-design or co-evolution of effective modularity

The role of modularity on internal state and memory:

• distributed and/or shared memory versus individual internal state
• cycles of interaction between modules or internal / external state

IMPORTANT DATES

• Submission deadline: December 15, 2026
• Notification of first review: January 26, 2027
• Submission of revised manuscript: March 26, 2027
• Notification of final decision: April 26, 2027

GUEST EDITORS

• Stephen Kelly, Affiliation: McMaster University, Hamilton, Canada, spkelly@mcmaster.ca
• Malcolm Heywood, Dalhousie University, Halifax, Canada,  mheywood@dal.ca

Call For Papers: Special Issue on Lexicase Selection

AIMS AND SCOPE

Springer Link here 

Lexicase selection selects individuals on the basis of their performance on training cases that are considered one at a time, in random order. First developed for parent selection in genetic programming, it has since been applied in other settings both within evolutionary computation and in other forms of machine learning [1,2].

Lexicase selection has been used, for example, for software synthesis, evolutionary robotics, multiobjective optimization, reinforcement learning, learning classifier systems (with a variant called batch lexicase selection), symbolic regression (with a variant called epsilon lexicase selection) and deep learning (with a variant called gradient lexicase selection). It has been analyzed with respect to selection efficiency, population diversity, the promotion of specialists, and problem-solving power, and such analyses have given rise to new methods such as informed downsampled lexicase selection and probabilistic lexicase selection.

This special issue of GPEM will focus on further studies of lexicase selection, its applications, its variants, and its analysis. It aims to draw together ideas from various perspectives to give a more holistic view of lexicase selection, helping guide future research and practice, deepening our understanding of how and why it works and when it should and shouldn't be used.

[1] T. Helmuth, L. Spector and J. Matheson, "Solving Uncompromising Problems With Lexicase Selection," in IEEE Transactions on Evolutionary Computation, vol. 19, no. 5, pp. 630-643, Oct. 2015, doi: 10.1109/TEVC.2014.2362729 

[2] Spector, L., Ding, L., Boldi, R. (2024). Particularity. In: Winkler, S., Trujillo, L., Ofria, C., Hu, T. (eds) Genetic Programming Theory and Practice XX. Genetic and Evolutionary Computation. Springer, Singapore. https://doi.org/10.1007/978-981-99-8413-8_9 

TOPICS OF INTEREST

• Analysis of the benefits and drawbacks of lexicase selection
• Analysis of applications that are amenable (or not) to lexicase selection
• Studies of variants of lexicase selection
• Creation of new variants of lexicase selection
• Critiques or position papers considering lexicase selection
• The lexicase algorithm used beyond parent selection
• Lexicase selection in contexts beyond genetic programming, including but not limited to other evolutionary algorithms, evolutionary robotics, reinforcement learning, and neural networks

IMPORTANT DATES

• Submission deadline: November 30, 2026
• Notification of first review: January 15, 2027
• Submission of revised manuscript: March 15, 2027
• Notification of final decision: April 15, 202

GUEST EDITORS

• Thomas Helmuth, Hamilton College, Clinton, United States, thelmuth@hamilton.edu 
• Lee Spector, Swoop Inc., United States,  lspector@amherst.edu 
• Edward Pantridge, Amherst College, Amherst Center, United States,  eddie.pantridge@gmail.com 

New Collections OPEN for Submission

 It is my pleasure to announce that 2 NEW Collections are open for submissions in Genetic Programming and Evolvable Machines, under the editorship of Ting Hu (Queen's University, Canada), our Special Communications Editor at the journal. 

These Collections will be published as Special Sections in the journal, namely

- Section: Comments and Correspondence: https://link.springer.com/collections/hhbhihfefd

- Section: Perspectives and Vision: https://link.springer.com/collections/ejjafdcebh

In both cases, the link gives a brief description of the aims and scope of each Collection, but if you have any further questions please contact me (leonardo.trujillo@tectijuana.edu.mx) or Ting Hu directly (ting.hu@queensu.ca).

SUBMISSION INSTRUCTIONS:

In both cases, if you intended to submit you must perform these steps in the Submission system:
1 Article Type: Authors should select “Correspondence” (for both collections)

2 Select the appropriate Collection for the submission (either Comments and Correspondence OR Perspectives and Vision)

Hope to continue to receive your excellent contributions to the journal!

Leonardo Trujillo

Editor in Chief

Genetic Programming and Evolvable Machines

Call for Papers: Special Issue on Generative AI and Evolutionary Computation for Software Engineering

 Special Issue Home: https://link.springer.com/collections/bcadcgjdjd

Generative models, and mainly large language models, are already widely used tools in real-world software development. They assist with writing code, generating tests, fixing bugs, and more. While these tools are powerful and quite useful, they still struggle with reliability, maintainability, and meeting complex requirements. This is where evolutionary algorithms, and especially genetic programming techniques, can make a decisive contribution. Unlike generative models that primarily rely on learned patterns, evolutionary algorithms offer a search-based approach to systematically explore the solution spaces. By combining the strengths of generative models with the flexibility and robustness of search-based techniques, we could build hybrid systems that produce even better and more reliable results.

The focus of this special issue is on the integration of generative methods and evolutionary computation to advance software engineering tasks. It aims to highlight approaches where evolutionary methods enhance, guide, or refine the output of generative models to produce better software solutions.

Topics of interest include, but are not limited to:

• Program Synthesis
• Requirements Engineering
• Prompt Engineering / Guided Prompt Search
• Genetic Improvement (functional and non-functional improvement)
• Code Transplantation
• Code Translation
• Automated Refactoring
• Clone Detection and Elimination
• Automated Program Repair
• Test Generation
• Test Suite Improvement
• Code Explanations & Interpretability
• Documentation Generation
• Semantic Code Search
• Human-AI Collaboration Tasks

Key Dates:

• Submission Deadline: 1 December 2025
• Reviews: 1 March 2026
• Revision Deadline: 15 April 2026
• Final Acceptance Notification: 15 May 2026

Links

• Special Issue Collection : https://link.springer.com/collections/bcadcgjdjd
• Journal Home: https://link.springer.com/journal/10710
• Submission Guidelines: https://link.springer.com/journal/10710/submission-guidelines

Guest Editor:

·        Dominik Sobania, Johannes Gutenberg University, Mainz, Germany (dsobania@uni-mainz.de)

Thematic Area

·        Software Engineering (Editor, Justyna Petke, University College London, UK)

ARC prize: a call to arms for Genetic Programming by Alberto Tonda

The Abstraction and Reasoning Corpus (ARC) is a benchmark designed to be easy to solve for humans and next to impossible for machine learning techniques which rely upon massive training data sets, like Deep Learning. Google's François Chollet, the author,  presents ARC as an attempt to push for AI algorithms able to "learn like humans" [1], or in other words, able to solve tasks after seeing just a small number of training instances, exploiting innate capacities to reason on geometry and number [2]. Just a few weeks ago, Chollet announced a Kaggle challenge on ARC, with a prize of 1 million $ [3] and a first deadline in November 2024, although submissions are already open [4].

I am not affiliated with the prize in any way, but I think this could represent a valuable opportunity for the GP/EA community: the tasks in ARC can be solved through *program synthesis*, as stated by Chollet himself [5], a function GP excels at; and the capacity of learning from a few samples is another strong suite of GP. Not to mention, just participating in the contest and comparing against other approaches could lead to cross-fertilization of new ideas, and even help promote GP as a robust AI alternative to the now more prominent DL approaches.

After discussing with colleagues, I decided to spread the news far and wide, in the hope that more and more people from our community would decide to take up the challenge. The current state of the art performance on ARC is still low (less than 40% accuracy on test at the time of writing), so the entry barriers should not be that high: now it's a good moment for GP researchers to take on the world and test our mettle!

[1] https://arxiv.org/pdf/1911.01547 

[2] https://aiguide.substack.com/p/why-the-abstraction-and-reasoning

[3] https://arcprize.org/competition

[4] https://www.kaggle.com/competitions/arc-prize-2024/

[5] https://arcprize.org/guide

Applications of Genetic Programming

An oft posed question is how much is genetic programming used, "for real"? https://gpbib.cs.ucl.ac.uk/gp-html/jaws30_reply.html Today, although many papers propose new types of GP, most are about applying GP.  Many papers use real world datasets to show how good a novel form of GP is or to compare GP and other AI approaches.   Instead lets concentrate upon papers where GP is just being used and the application itself is the important thing.

Of course most industrialists are not interested in papers.  Indeed they may have sound commercial reasons for not publicising their results or even what they are interested in. Which always means numbers based on published work will be an underestimate.

Nonetheless, taking data for 2023 in the genetic programming bibliography https://gpbib.cs.ucl.ac.uk/ today as typical, about 38% (pm 5%) of papers are on applications.  About a quarter of all GP papers are on: Medicine, Civil Engineering or Material Science, often with an environmental or sustainability emphasis.

Humies 2024, closes Friday 31 May

A quick reminder GP+EM articles published after 2 June 2023 are eligible to enter this year's Human Competitive awards (competition closes to new entries on Friday May 31). Full details on line: https://human-competitive.org/call-for-entries

As with last year, the Humies will be held in hybrid mode, i.e. both in person in Melbourne and online, via video link. Prize money will be sent to the winners via wire transfer.

Entries listed in https://human-competitive.org/awards

The finalists who will battle it out to convince the judges they should be the winner have been announced on  https://human-competitive.org/awards