Beautifully situated between the Pyrenees, the Mediterranean Sea, and the Atlantic Ocean, Toulouse is the capital of the Occitanie region and one of the most vibrant cities in southwestern France. Recently ranked among the world's top cities to visit, Toulouse attracts millions of tourists each year with its charming historic center, stunning scenery, renowned gastronomy, and lively cultural scene. Yet it is not only visitors who are drawn to the "Ville Rose" — the Pink City — named after the distinctive red bricks used throughout its architecture.
The GECCO 2026 Conference was held July 13–17 this year, once again in hybrid mode. Around 400 people came to San José, Costa Rica to attend in person, and an additional 200 or so registered to attend virtually. The finals of the Humies competition (see www.human-competitive.org for the Call for Entries) was a plenary session on Wednesday, July 15, that was attended by about 75 people. The six finalists earlier selected by the judges (from among 9 entries this year, and based on the papers and entry forms they submitted) presented their work in 10-minute talks, or, in three cases, a pre-recorded video.
Every research career has to start somewhere. For most people in evolutionary computation, that somewhere is a PhD program. For me, it started in a robotics Co-Curricular Activity (CCA) in Ang Mo Kio Primary School and, a decade of curiosity later, led to a workshop paper at GECCO 2026 in San José, Costa Rica. This is the story of how a Differential Evolution algorithm and a lot of patient mentorship turned a schoolboy's curiosity into a peer-reviewed paper.
In 2012, researchers in the genetic programming community realized that the field was being held back by reliance on toy benchmark problems [1]. By 2015, some work had been done to improve benchmarking in specialized areas such as symbolic regression [2]. However, no standardized benchmark problems had yet been developed for general program synthesis, the task of automatically generating programs that are similar in many respects to the kinds of programs that humans usually write.
This dissertation explores how optimization algorithms can become both more effective and more interpretable. It focuses on two long-standing limitations of metaheuristics: first, their frequent lack of awareness of the specific structure of the problem they are solving; and second, their opacity, which makes it difficult to understand why they behave well in some cases and poorly in others.
