============
Call for Papers
============

29th International Workshop on Evolutionary Rule-based Machine Learning IWERL 2026 (formerly IWLCS)
to be held as part of GECCO (July 13 - 17, 2026) in San José, Costa Rica (online participation possible)

Modern machine learning systems, including generative AI and large language models, offer significant potential for addressing real-world challenges. However, the decision-making process of the majority of these models is often difficult to interpret. The interpretability of decisions is critical in many real-world applications. Evolutionary rule-based machine learning (ERL) systems generate niche-based solutions, require less memory, and can be trained using comparatively small data sets. The decision-making process of the ERL systems is interpretable, which is an important step toward eXplainable AI (XAI).

ERL methods have been developed using a diverse array of learning paradigms, including supervised learning, unsupervised learning, and reinforcement learning. ERL encompasses several prominent categories, such as Learning Classifier Systems, Ant-Miner, artificial immune systems, and fuzzy rule-based systems. The International Workshop on Evolutionary Rule-based Machine Learning (IWERL) is designed to provide a platform for sharing the research trends in the realm of ERL. It aims to highlight modern implementations of ERL systems for real-world applications and to show the effectiveness of ERL in creating flexible and eXplainable AI systems. The particular topics of interest of this workshop are (not exclusively):

•     Advances in ERL methods: local models, problem space partitioning, rule mixing, . . .
•     Applications of ERL: medical domains, bioinformatics, computer vision, games, cyber-physical systems, . . .
•     State-of-the-art analysis: surveys, sound comparative experimental benchmarks, carefully crafted reproducibility studies, . . .
•     Formal developments in ERL: provably optimal parametrization, time bounds, generalization, . . .
•     Comprehensibility of evolved rule sets: knowledge extraction, visualization, interpretation of decisions, XAI, . . .
•     Advances in ERL paradigms: Michigan/Pittsburgh style, hybrids, iterative rule learning, . . .
•     Hyperparameter optimization for ERL: hyperparameter selection, online self-adaptation, . . .
•     Optimizations and parallel implementations: GPU acceleration, matching algorithms, . . .
•     Generative AI and LLMs in ERL: Integration of generative models and LLMs with ERL, . . .

Submission deadline:                     March 27, 2026
Decision notification:                     April 24, 2026
Camera-ready deadline:                   May 5, 2026
Author's mandatory registration:    May 11, 2026

Why submit to IWERL ’26?

•     reviews by renowned ERL experts
•     published as part of the GECCO conference companion
•     usually online within one month after the conference

Submissions

• This workshop accepts two types of submissions:
•  research papers on novel findings or improvements
•  position papers making a concise argument based on preliminary findings
• All submissions must conform to the GECCO submission instructions (https://gecco-2026.sigevo.org/Paper-Submission-Instructions) and be submitted via GECCO’s submission system (https://ssl.linklings.net/conferences/gecco/). 
• In 2026, you can submit either 8 pages (excl. references) with APC or 4 pages (incl. references) without APC.

Workshop organization

• Michael Heider, University of Augsburg, Germany
• Hiroki Shiraishi, Yokohama National University, Japan
• Fumito Uwano, Okayama University, Japan
• Connor Schönberner, Kiel University, Germany

More information can be found at https://iwlcs.organic-computing.de