Microcosmos: Reimagining Artificial Life for the GPU Era
It provides a physically plausible and computationally scalable platform for large-scale open-ended evolutionary simulations, addressing the bottleneck of previous simulators that either lacked physical grounding or could not scale to large populations.
Microcosmos is a GPU-accelerated artificial life simulator that models lifeforms as elastic filament chains in a 2D viscous fluid, achieving linear scaling with particle count and enabling gradient-based optimization, neuroevolution, and quality-diversity search for diverse behaviors.
Most artificial life simulators either operate on abstract substrates disconnected from physical reality, or simulate physically grounded worlds that do not scale to the population sizes required for open-ended evolution. We present Microcosmos, a simulation engine in which artificial lifeforms are modeled as elastic filament chains inhabiting a two-dimensional viscous fluid world, designed from the ground up for modern GPU hardware and end-to-end differentiable simulation. We validate the engine through four experiments. Hand-designed locomotion strategies confirm that the fluid coupling respects known physical constraints. Gradient-based optimization of filament folding demonstrates both the full differentiability of the simulator and the expressivity of the filament encodings. Neuroevolution and quality-diversity search produce a wide range of swimming and chemotaxis behaviors automatically. Linear scaling with particle count confirms the engine supports large-scale simulation. Microcosmos is released as an open platform with the long-term goal of supporting large-scale open-ended evolutionary simulations, designed to be physically plausible and computationally scalable.