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; Harold Soh

cs.ROMar 4, 2026

SkillVLA: Tackling Combinatorial Diversity in Dual-Arm Manipulation via Skill Reuse

Authors: Xuanran Zhai, Zekai Huang, Longyan Wu, Qianyou Zhao, Qiaojun Yu, Jieji Ren, Ce Hao, Harold Soh

Organizations: National University of Singapore · Shanghai Innovation Institute · Fudan University · Shanghai Jiao Tong University · Shanghai AI Laboratory · Beijing Zhongguancun Academy · Smart Systems Institute, NUS

Abstract

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.

Figures & tables

Fig. 2 : SkillVLA framework. SkillVLA adopts a two-level reasoning pipeline, where the high-level VLM generates separate subtasks for arms and low-level VLMs further process the prompts to instruct action generation. Inter-arm cross-attention enables cooperative behaviors generation, controlled by a collaboration estimator that identifies the operation mode required.

Fig. 3 : Skill recomposition tasks. (A): The models are trained on demonstrations of three skills for each arm. (B): After the models have learned the skills, zero-shot tests are conducted for every possible combinations of left and right-arm skills.

Methods	Recomposition Tasks
Methods	Cup $\times$ Cake	Cup $\times$ Stir	Cup $\times$ Smash	Box $\times$ Cake	Box $\times$ Stir	Box $\times$ Smash	Mug $\times$ Cake	Mug $\times$ Stir	Mug $\times$ Smash	Avg.
$\pi_{0.5}$	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
$\pi_{0}$ -FAST	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
TwinVLA	0.1	0.0	0.0	0.2	0.0	0.1	0.0	0.0	0.0	0.04
SkillVLA	0.7	0.4	0.5	0.6	0.4	0.5	0.6	0.3	0.6	0.51

TABLE I : Success Rates on Skill Recomposition Tasks

\uparrow

Methods	Skills Learned
Methods	Cup	Box	Mug	Cake	Stir	Smash	Avg.
$\pi_{0.5}$	0.7	1.0	0.8	0.8	0.6	0.7	0.77
$\pi_{0}$ -FAST	0.9	0.8	0.7	0.9	0.5	0.4	0.70
TwinVLA	0.7	0.8	0.5	0.8	0.5	0.7	0.67
SkillVLA	0.8	0.7	0.8	1.0	0.6	0.8	0.78

TABLE II : Success Rates on Skills Learned

Fig. 4 : Cooperative tasks. (a) Shake : Shake the cup with a cap without making them fall apart. (b) Ball : Lift the ball steadily. (c) Align : Align the blocks on the table.

Fig. 5 : Long-horizon tasks behaviors and results. Top: Behavior of $\pi_{0.5}$ in Tubes . Middle left: Behavior of SkillVLA in Tubes . Bottom left: Changes of $\alpha$ values throughout the completion, respectively from SkillVLA and an ablated version without discretization of $\alpha$ . Bottom right: Averaged progress score and completion time of methods on the long-horizon tasks.

Fig. 6 : Continual learning tasks and results. Left: SkillVLA in continual learning tasks, Lift bag and Shake cup . Right: Success rates on cooperative tasks Lift bag and Shake cup w.r.t the number of continual learning demonstrations.

Methods	Shake	Ball	Align	Avg.
$\pi_{0.5}$	0.30	0.45	0.65	0.47
TwinVLA	0.15	0.55	0.55	0.42
SkillVLA	0.25	0.50	0.70	0.48
SkillVLA w/o Attn.	0.00	0.10	0.40	0.17

TABLE III : Success Rate in Cooperative Tasks

\uparrow

Appendix figures & tables4 assets

Supplementary material from the paper’s appendix.

Appendix

Abbr.	Task	Description
Shake	Shake Cup	A cup with a loose cap is placed on the table. The robot must shake the cup bimanually, with one arm securing the cap to prevent separation. This requires the arms to move synchronously to maintain the assembly’s integrity.
Lift	Lift Ball	A ball rests on a stand. The robot must lift the ball using both arms. The upward motion must be synchronized in velocity to maintain equilibrium and prevent the ball from rotating or falling.
Align	Align Blocks	Two blocks are placed on the table. The robot must grasp one block with each arm and place them onto the table simultaneously such that they align collinearly.

Appendix

TABLE IV : Cooperative Task Details

Fig. 7 : Rollout of SkillVLA on Collect Items .

Fig. 9 : Skills Learned for Collect Items .

Explore similar work

Co-VLA: Coordination-Aware Structured Action Modeling for Dual-Arm Vision-Language-Action Systems
Jun 18, 2026Yandong Wang, Jiaqian Yu, Xiongfeng Peng +8Bimanual Robotic Manipulation Vision-Language-Action Models
Donghua University, Shanghai, China · Samsung R&D Institute China-Beijing (SRCB), China · Samsung AI Center, DS Division, South Korea
Arm-wise Compositional Generalization in Dual-Arm Vision-Language-Action Models
Oct 5, 2026Zaibin Zhang, Binghao Ran, Yuhan Wu +10Bimanual Robotic Manipulation Vision-Language-Action Models
Dalian University of Technology · Shanghai Jiao Tong University · The Chinese University of Hong Kong, Shenzhen +1
See Selectively, Act Adaptively: Dual-Level Structural Decomposition for Bimanual Robot Manipulation
Jun 11, 2026Yoon-Ji Choi, Young-Chae Son, Soo-Chul LimLong-Horizon Robotic Manipulation Bimanual Robotic Manipulation
Dongguk University

Jun 18, 2026J/K move · Enter open · S save

Co-VLA: Coordination-Aware Structured Action Modeling for Dual-Arm Vision-Language-Action Systems

Yandong Wang, Jiaqian Yu, Xiongfeng Peng, Lu Xu+7

Donghua University, Shanghai, China · Samsung R&D Institute China-Beijing (SRCB), China · Samsung AI Center, DS Division, South Korea

Bimanual Robotic Manipulation Vision-Language-Action Models

Open paper AskPDF arXiv

Vision-language-action (VLA) models show strong capabilities in single and dual-arm robotic manipulation. Prior works show coordinated bimanual behaviors can emerge from end-to-end learning, leveraging large vision-language backbones with continuous action prediction. However, as bimanual tasks become tightly coupled and execution constraints become critical, implicit coordination alone is insufficient to ensure reliable, interpretable, and stable behavior. In this work, we propose Co-VLA, a coordination-aware bimanual manipulation framework introducing explicit structural priors into VLA models. We instantiate our method on a state-of-the-art vision-language backbone by replacing its monolithic action head with a Structured Action Expert (SAE) designed for bimanual coordination. Specifically, we introduce explicit structure at the action generation level with a modular coordination-aware loss that shapes shared and residual latents according to task-specific structures. The shared latent encodes task-level coordination intent, while residual latents capture execution adjustments for each arm. At deployment, a Latent-Aware Controller (LAC) interprets the learned representations to modulate synchronization strength, execution asymmetry, smoothness, and safety constraints in real time. LAC operates at the joint-command level and remains compatible with standard control pipelines without requiring force or impedance control. Experiments across simulation and real-world benchmarks show Co-VLA significantly outperforms monolithic baselines, achieving a 27% success rate gain in tight-coordination tasks, more than doubling performance in OOD real-world scenarios (from 13% to 27%), and reducing task completion time by up to 25%.

Abstract

Explore similar work

Co-VLA: Coordination-Aware Structured Action Modeling for Dual-Arm Vision-Language-Action Systems

Arm-wise Compositional Generalization in Dual-Arm Vision-Language-Action Models

See Selectively, Act Adaptively: Dual-Level Structural Decomposition for Bimanual Robot Manipulation