ASH: Agents that Self-Hone via Embodied Learning 事件

ASH: Agents that Self-Hone via Embodied Learning arXiv:2605.14211v2 Announce Type: replace Abstract: Long-horizon embodied tasks remain a fundamental challenge in AI, as current methods rely on hand-engineered rewards or action-labeled demonstrations, neither of which scales. We introduce ASH, an agentic system that learns an embodied policy from unlabeled, noisy internet video, without reward shaping or expert annotation. ASH follows a self-improvement loop; when it gets stuck, ASH learns an I