Recent progress in vision-language-action (VLA) models has demonstrated strong potential for dual-arm manipulation, enabling complex behaviors and generalization to unseen environments. However, mainstream bimanual VLA formulations largely overlook the critical challenge of combinatorial diversity. Different pairings of single-arm behaviors can induce qualitatively distinct task behaviors, yet existing models do not explicitly account for this structure. We argue that effective bimanual VLAs should support skill reuse - the ability to recombine previously learned single-arm skills across novel left-right pairings - thereby avoiding the need to separately learn every possible combination. Current VLA designs entangle skills across arms, preventing such recomposition and limiting scalability. To address this limitation, we propose SkillVLA, a framework explicitly designed to enable skill reuse in dual-arm manipulation. Extensive experiments demonstrate that SkillVLA substantially improves skill composition, increasing overall success rate from 0% to 51%, and achieves strong performance on cooperative and long-horizon tasks.
@article{arxiv.2603.03836,
title = {SkillVLA: Tackling Combinatorial Diversity in Dual-Arm Manipulation via Skill Reuse},
author = {Xuanran Zhai and Zekai Huang and Longyan Wu and Qianyou Zhao and Qiaojun Yu and Jieji Ren and Ce Hao and Harold Soh},
journal= {arXiv preprint arXiv:2603.03836},
year = {2026}
}