Sandman: Building and Operating Sandboxes for Agentic Reinforcement Learning on Shared Kubernetes
arXiv:2610.39711v1 Announce Type: cross Abstract: Agentic reinforcement learning (RL) often requires repeated tool calls in task-specific environments. A training job may create thousands of these environments in bursts while sharing a cluster with other jobs. We present Sandman, a sandbox service built and operated at Amazon for agent tool execution and evaluation. It serves multiple production agentic RL workloads on shared Kubernetes. A training framework supplies a task image and uses comma…