article-journal

This study explores integrating large language models (LLMs) into multi-agent simulations, replacing hard-coded agent programs with LLM-driven prompts. The approach is demonstrated using examples of ant colony foraging and bird flocking, enabling the study of self-organizing processes and emergent behaviors in multi-agent environments.

The Human Brain Project (HBP) Education Programme addressed the challenges of interdisciplinary neuroscience education by training over 5,500 participants across neuroscience, medicine, and IT over a decade, fostering collaboration and adaptability. The programme succeeded in reaching a diverse audience and establishing transversal collaborations, with lessons learned emphasizing the importance of digital tools for future training initiatives in decentralized settings.

We show how a multi-agent system (ant colony) steered by Spiking Neural Networks establishes self-organization while foraging for food. We evolve the networks using a genetic algorithm and learning to learn. Our results depict emergent behavior, which we investigate.

Experimental evidence suggests that brain-state-specific neural mechanisms play a crucial role in integrating past and contextual knowledge with current sensory information, operating across multiple spatial and temporal scales. A new two-compartment spiking neuron model has been developed to support brain-state-specific learning, incorporating features such as apical amplification and isolation, and utilizing a piece-wise linear transfer function to make it suitable for large-scale bio-inspired artificial intelligence systems.

Neuroscience models commonly have a high number of degrees of freedom and only specific regions within the parameter space are able to …