Loading...
 
Skip to main content

Program Synthesis Workshop

Webpage:

Description

Program Synthesis (PS) is the task of automatically generating executable programs from high-level specifications, such as logical constraints, input-output examples, or natural language descriptions. Inside the evolutionary community, PS is often seen as an established application of Genetic Programming (GP), but the broader PS community has developed a variety of different approaches, ranging from program enumeration with constraints, to Monte-Carlo tree search, to Large Language Models (LLMs). In recent years, hybrid approaches combining different techniques have begun to emerge, pushing PS towards better and better results.

A recent publication in the 2025 Genetic Programming: Theory and Practice conference, authored by one of organizers of this workshop, advocated for building a bridge between the evolutionary community and non-evolutionary approaches to PS. Following this idea, this workshop aims to encourage the evolutionary community to focus more on PS, at the same time, creating bridges with other PS approaches, in the hope of obtaining even more performing hybrid forms.

Scope:

The scope of the workshop includes, but is not limited to, the following PS-related topics:
• GP Representations for Program Synthesis (e.g., Tree-based, Linear, Graph)
• Fitness functions (Single vs Multi-objective, Test Integration, Coverage, Specification fulfill-
ment)
• Formal methods for Program Synthesis
• Inductive logic programming
• Deductive Program Synthesis
• LLM-based Program Synthesis
• Agentic approach for Program Synthesis
• Hybrid methods for Program Synthesis
• Program Benchmarks
• Program Synthesis for general AI tasks, such as the Abstraction and Reasoning Corpus1
• Non-conventional applications (e.g., theorem proving, infrastructure configuration)
• Real-world applications of Program Synthesis

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, 2026 April 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

Alberto Tonda

Alberto Tonda received his Ph.D. degree in Computer Science Engineering from Politecnico di Torino, Italy, in 2011. Currently, he is a Permanent Researcher (CRCN) at the National Institute of Research for Agriculture and Environment (INRAE), and Université Paris-Saclay, Paris, France. His research interests include semi-supervised modeling of complex systems, evolutionary optimization and machine learning, with main applications in food science and biology. He led COST Action CA15118 FoodMC, a 4-year European networking project on in-silico modelling in food science. He published over 30 contributions in peer-reviewed journals, and over 60 conference papers. He was part of the program committee of 10 conferences of the domain, and he is currently an editorial board member of the journal Genetic Programming and Evolvable Machines.

Alcides Fonseca

Alcides Fonseca is an Assistant Professor at the University of Lisbon, and the Reliable Software Systems research line leader at LASIGE. He has a PhD in automatic optimization of parallel programs by the University of Coimbra. Alcides leads the LASIGE side of the CAMELOT project, that aims to improve the machine learning development process in collaboration with Feedzai, U. Coimbra, IST and CMU. He is also the PI of Resource Aware Programming, a project that aims to give programmers immediate feedback on the energy consumption of their code. He is also a consultant with Genomed, a genetics diagnosis company and a mentor at Decipad, a company that is re-inventing spreadsheets as computable documents.

 
Fabricio Olivetti de França

Fabricio Olivetti de França is an associated professor in the Center for Mathematics, Computing and Cognition (CMCC) at Federal University of ABC. He received his PhD in Computer and Electrical Engineering from State University of Campinas. His current research topics are Symbolic Regression, Evolutionary Computation and Functional Data Structures.

Giovanni Squillero

Giovanni Squillero is a full professor of Computer Science at Politecnico di Torino, Department of Control and Computer Engineering. His research combines artificial intelligence and soft computing, in particular bio-inspired meta-heuristics and multi-agent systems. He also designs approximate optimization techniques able to achieve acceptable solutions with reasonable amount of resources. The industrial applications of his work range from electronic CAD to bioinformatics, to the cultural sector. As of October 2024, Squillero is credited as an author in about 200 publications and as an editor in 14 volumes. He has presented several tutorials at top conferences, and he has been invited to speak at international events. Squillero was the Program Chair of EvoSTAR in 2016 and 2017. He (co-)organized the workshops on Graph Genetic Programming (GECCO24); Evolutionary Machine Learning (PPSN18); Measuring and Promoting Diversity in Evolutionary Algorithms (GECCO16-17); Evolutionary Hardware Optimization (EvoSTAR04-14). As an entrepreneur, he co-founded Ominee, S.r.l. in 2014, Bactell, Inc. in 2019, and Ai·Culture, S.r.l. in 2024.

Thomas Helmuth

Thomas Helmuth, PhD Assistant Professor of Computer Science, Hamilton College Thomas is an assistant professor of computer science at Hamilton College in New York. He received his Ph.D. from University of Massachusetts Amherst working with professor Lee Spector. His research focuses on applications of genetic programming to automatic software synthesis. He has contributed to genetic programming in the areas of parent selection, stack-based program representations (in particular Push), and the benchmarking of program synthesis systems.