BEAST: A Tensor-Oriented Approach to Population-Scale Agent-Based Simulation

Agent-based models (ABMs) offer a compelling framework for simulating complex systems but scale poorly with conventional software execution paradigms. When modelling millions of interacting agents with complex lifecycles and spatial dynamics, conventional ABMs encounter severe computational bottlenecks, e.g., from memory fragmentation and loop-based state updates.We introduce BEAST (Big and Efficient Agent-based Simulation using Tensors), a tensor-oriented approach that reformulates agent state, interactions, and transitions as tensor programs, which enables population-level vectorised computation on commodity GPU hardware. BEAST supports heterogeneous agent attributes, stochastic state transitions, spatially explicit movement, and machine-learning–driven behaviours, while eliminating the traditional trade-off between expressiveness and computational scale. Applied to modelling of gene drive mosquito dynamics on Pr´ıncipe Island, BEAST can simulate millions of individual agents with full lifecycle, genetic inheritance, and spatial dispersal fidelity, demonstrating that a single strategically placed release achieves 95% allele prevalence within approximately 73 days. The emergent Allee effect threshold at ∼300 individuals further validates the model’s ecological fidelity. These results demonstrate that our tensor-oriented reformulation enables population-scale agent-based simulation without sacrificing behavioural richness.