GPUSimBench Reveals Hidden Limits in GPU-Accelerated Simulators for Embodied AI

Jul 16, 2026

A new benchmark, GPUSimBench, systematically evaluates GPU-accelerated simulators used in embodied AI, such as Isaac Lab and Genesis, uncovering critical trade-offs between scalability, physical fidelity, and computational determinism. The study demonstrates that as simulation throughput increases, non-determinism and variability across parallel environments become significant, with four distinct regimes of stochasticity identified. These findings suggest that current GPU-based simulators may compromise reproducibility in large-scale robot learning unless explicit constraints are imposed.

Why it matters: Understanding and addressing non-determinism in GPU-accelerated simulators is essential for ensuring reliable and reproducible training in large-scale embodied AI systems.

Full story at: arXiv Robotics ↗