HiSTEVE 1.0: Harnessing Human-Interface VLA Agents for Open-World Games

HiSTEVE 1.0 is a hierarchical VLA agent with a capability-aware agent harness designed for open-world games like Minecraft, combining a VLM planner for subtask selection with a single VLA that executes subtasks using vision-only perception and native keyboard-and-mouse actions.