Search papers, labs, and topics across Lattice.
This paper introduces MA-VLA, a novel framework for multi-arm collaboration in embodied manipulation that enhances vision-language-action models by enabling atomic action assignment for individual arms. By decomposing cooperative behaviors into mid-level atomic prompts and employing a training technique called Arm Shuffle, MA-VLA facilitates role-agnostic instruction following and supports compositional generalization across unseen collaboration patterns. Experimental results demonstrate that MA-VLA outperforms existing state-of-the-art models in both simulated and real-world scenarios, indicating its effectiveness in achieving scalable generalization in multi-arm systems.
MA-VLA enables multi-arm systems to generalize to unseen collaboration patterns, outperforming prior models that struggle with such tasks.
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 allocates them to individual arms, enabling explicit subgoal specification and compositional reuse across tasks. To reduce reliance on fixed execution roles, we introduce Arm Shuffle, a training-time permutation of the observation, state, and assigned atomic prompts for each arm. This permutation enforces role-agnostic instruction following and supports recomposition into unseen coordination patterns, which we term multi-arm compositional generalization. We also construct a benchmark in which test-time collaboration patterns are absent in training set. Across simulation and real-world evaluations, prior state-of-the-art VLAs largely fail under these unseen collaborations, while MA-VLA consistently succeeds. These results indicate that structured, per-arm atomic action assignment offers a practical route to scalable generalization in multi-arm embodied systems. Code, models, and data are available at https://github.com/zhangzaibin/future-robots
