Skill-Decoupled On-Policy Expert Distillation for Unified Vision-Language Models

Reinforcement learning (RL) can elicit specialized visual capabilities in visionlanguage models (VLMs), yet jointly optimizing heterogeneous objectives often
introduces cross-capability gradient conflicts. Training experts independently mitigates this interference, but direct reward optimization may entangle specialized
knowledge with reward-hacking biases. This paper proposes Skill-Decoupled OnPolicy Expert Distillation (SCOPED), which trains capability-specific experts and
extracts explicit skills through reward-guided reflection. During on-policy distillation, these skills guide expert supervision while remaining unavailable to the
unified student, encouraging it to internalize procedural knowledge without explicit skills at inference time. Across eight multimodal benchmarks, SCOPED
consistently outperforms the backbone and mixed-capability RL, demonstrating
the effectiveness of skill-decoupled on-policy expert distillation for integrating
independently acquired capabilities. Further analyses reveal interference during
joint capability optimization and suggest that skill augmentation promotes more
consistent expert trajectories, greater attention to task-relevant visual evidence,
and better preservation of specialized expertise in the unified student.