SOURCE-LINKED INTELLIGENCE

TaskAnchor: Grounding Task State in Reactive VLAs for Long-Horizon Manipulation

arXiv · AI, language, vision and robotics · article · Sep 20, 2026 · UTC

Reactive vision--language--action (VLA) models struggle with long-horizon manipulation when visually similar observations can correspond to different actions depending on the task stage or interaction history. We refer to this ambiguity as task-state aliasing and introduce TaskAnchor, a lightweight adapter that grounds pretrained VLAs in execution history. TaskAnchor combines history-conditioned visual refinement with a milestone-supervised task-state coordinate, a scalar representing the semantic stage of execution. These signals are injected through the native visual and language interfaces,

Read original source ↗ Open in workspace

recordType

paper

region

Global