Ask-to-Clarify: Resolving Instruction Ambiguity through Multi-turn Dialogue 事件

Ask-to-Clarify: Resolving Instruction Ambiguity through Multi-turn Dialogue arXiv:2509.15061v2 Announce Type: cross Abstract: The ultimate goal of embodied agents is to create collaborators that can interact with humans, not mere executors that passively follow instructions. This requires agents to communicate, coordinate, and adapt their actions based on human feedback. Recently, advances in VLAs have offered a path toward this goal. However, most current VLA-based embodied agents operate in a