SkillVLA: Tackling Combinatorial Diversity in Dual-Arm Manipulation via Skill Reuse, Xuanran Zhai★, Zekai Huang★, Longyan Wu, Qianyou Zhao, Qiaojun Yu, Jieji Ren, Ce Hao★, and Harold Soh★, Robotics: Science and Systems (R:SS)
Links:
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. SkillVLA automatically identifies skill structures from demonstrations and performs skill-adaptive action generation through a two-level reasoning architecture, retrieving single-arm skills as independent units while capturing inter-arm dependence when collaboration is required. 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.
Resources
You can find our paper here.
Citation
Please consider citing our paper if you build upon our results and ideas.
Xuanran Zhai★, Zekai Huang★, Longyan Wu, Qianyou Zhao, Qiaojun Yu, Jieji Ren, Ce Hao★, and Harold Soh★, “SkillVLA: Tackling Combinatorial Diversity in Dual-Arm Manipulation via Skill Reuse”, Robotics: Science and Systems (R:SS)
@inproceedings{zhai2026skillvla, title={SkillVLA: Tackling Combinatorial Diversity in Dual-Arm Manipulation via Skill Reuse}, author={Zhai, Xuanran and Huang, Zekai and Wu, Longyan and Zhao, Qianyou and Yu, Qiaojun and Ren, Jieji and Hao, Ce and Soh, Harold}, booktitle={Robotics: Science and Systems (R:SS)}, year={2026} }
Contact
If you have questions or comments, please contact Ce Hao or Harold.
