Evolutionary Algorithms and Applications

Selection navigates a degenerate circuit space: behavioral individuation without structural differentiation in constrained neuroevolution

The paper shows that individual-target selection in constrained neuroevolution leads to behavioral individuation through functional sensitivity commitment, not structural differentiation.

Genomebook: Mendelian inheritance as a structured parameterisation layer for LLM agent populations

This paper introduces Genomebook, a system that encodes genetic inheritance in LLM agents, showing trait changes over generations under selective pressures.

LLM-Evolved Regularization Schedules Prevent Posterior Collapse in Latent Factor Analysis via Dynamical Systems

The paper evolves regularization schedules using LLMs to prevent posterior collapse in LFADS without population-based training, improving KL divergence and stability.

Discovering Symbolic Cognitive Models from Human and Animal Behavior

LLM-driven evolutionary program synthesis (CogFunSearch) discovers interpretable Python cognitive models that predict bandit-task choices of humans, rats and fruit flies better than leading hand-designed models.

Global Progress in Competitive Co-Evolution: a Systematic Comparison of Alternative Methods

This study compares four competitive co-evolution algorithms to assess their ability to achieve global progress in a predator-prey scenario.