SOURCE-LINKED INTELLIGENCE

GeoAAC: Geometry-Based Adaptive Action Chunking from Denoising Trajectories in VLA Policies

arXiv · Artificial Intelligence · article · Sep 17, 2026 · UTC

Action chunking is widely used for action generation and execution in Vision-Language-Action (VLA) policies, yet existing approaches commonly use a fixed action horizon. During a rollout, different task stages may require different levels of action continuity, control precision, and closed-loop feedback, making a fixed horizon unable to accommodate changing control requirements. We propose \textbf{GeoAAC}, a geometry-based adaptive action chunking method for flow-based VLA policies that adjusts the action horizon according to the reliability of the current action prediction. We show that the g

Read original source ↗ Open in workspace

recordType

paper

region

Global