A hands-on SAB 2026 tutorial with JAX, Kozax, and ABMax
SAB 2026 — From Animals to Animats 18
Berlin, Germany · October 2026 · Half-day tutorial
How can we design complex systems that behave adaptively while being interpretable at the same time?
In this hands-on tutorial, participants will learn how genetic programming and symbolic regression can be used to discover compact, readable update rules for agent-based models. We combine Kozax, a scalable genetic programming library in JAX, with ABMax, a JAX-based agent-based modelling framework, to construct and evaluate interpretable models of complex adaptive systems.
The tutorial introduces core ideas through a practical consensus task: agents must combine noisy individual information with local social information. Participants will use genetic programming to discover an agent update rule and compare the resulting equation with a known hand-designed mechanism.
This tutorial is aimed at researchers and students interested in any of the following:
Prerequisites: Basic familiarity with Python, JAX, genetic programming and agent-based modelling is helpful. A primer on JAX, genetic programming, and agent-based modelling will be provided.
By the end of the tutorial, participants will be able to:
| Session | Topic |
|---|---|
| Introduction | Complex adaptive systems, agent-based models, and interpretable agent rules |
| JAX Primer | Arrays, vectorisation, random numbers, and just-in-time compilation |
| Genetic Programming with Kozax | Search spaces, candidate expressions, objectives, and selection |
| Agent-Based Modelling with ABMax | Agents, states, parameters, and update functions |
| Hands-on Exercise | Discovering an interpretable rule for a local consensus task |
| Discussion | Interpreting discovered mechanisms and extending the pipeline |
Agents move in a shared environment while maintaining an internal estimate of a hidden target. Some agents receive noisy information about the target; others observe only nearby neighbours.
Participants will use genetic programming to search for a compact local update rule that combines social information with self-pinning. The discovered expression is then evaluated inside a scalable agent-based simulation built with ABMax.
Please bring a laptop capable of running Python notebooks.
Installation instructions, tutorial notebooks, and supporting materials will be added to this repository before the conference.
| Resource | Status |
|---|---|
| Tutorial repository | Coming soon |
| Installation instructions | Coming soon |
| Slides | Coming soon |
| Jupyter notebooks | Coming soon |
Siddharth Chaturvedi
Department of Machine Learning and Neural Computing, Donders Institute for Brain, Cognition and Behaviour, Radboud University.
Siddharth is a developer of ABMax, a JAX-based framework for scalable agent-based modelling. His research focuses on adaptive behaviour, agent-based artificial intelligence, and complex systems.
Sigur de Vries
Department of Machine Learning and Neural Computing, Donders Institute for Brain, Cognition and Behaviour, Radboud University.
Sigur is a developer of Kozax, a flexible and scalable genetic programming library implemented in JAX.
Artificial Cognitive Systems lab led by prof. Marcel van Gerven, studies the computational mechanisms of learning, inference and control in natural and artificial systems. To this end, we bring together ideas from a wide range of disciplines such as machine learning, computational neuroscience, control theory, dynamical systems theory, statistical physics and theoretical biology. Ultimately, our goal is to bridge the gap between natural and artificial intelligence and contribute more capable and efficient AI solutions to address a wide variety of scientific and societal challenges.
For questions about the tutorial, please contact:
Siddharth Chaturvedi — siddharth.chaturvedi@donders.ru.nl
For general conference information, visit the SAB 2026 website.
This tutorial is part of SAB 2026 — From Animals to Animats 18, Berlin, 19–22 October 2026.