SOURCE-LINKED INTELLIGENCE

MA-VLA: Multi-Arm Vision-Language-Action Model for Collaboration and Compositional Generalization

arXiv · AI, language, vision and robotics · article · Aug 26, 2026 · UTC

Multi-arm collaboration is becoming a core capability in embodied manipulation. Recent vision-language-action (VLA) models integrate perception, language, and control, but most represent language as a single global instruction and do not provide an explicit mechanism for assigning and composing arm-specific behaviors. This design limits transfer to collaboration patterns that differ from those observed during training. We present MA-VLA, a unified framework for multi-arm collaboration via atomic action assignment. MA-VLA decomposes cooperative behavior into mid-level atomic prompts and allocat

Read original source ↗ Open in workspace

recordType

paper

region

Global