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

Abstract: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, respectively, without introducing an explicit planner or modifying the action-generation mechanism. On RMBench, TaskAnchor achieves approximately 4.9--5.5$\times$ the average success rates of the published $\pi_{0.5}$ and X-VLA baselines, with consistent gains on RoboMemArena and real robots. The added latency is only 2.08\,ms per action chunk for $\pi_{0.5}$.

Robotics (cs.RO)

arXiv:2609.23580 [cs.RO]

(or arXiv:2609.23580v1 [cs.RO] for this version)

https://doi.org/10.48550/arXiv.2609.23580 Focus to learn more arXiv-issued DOI via DataCite (pending registration)

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.