swarm intelligence

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.

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.