we introduce Decoupled Policy Optimization (DePO). By identifying the geometric and variance mismatches inherent in standard RL， we propose HyLaR (Hybrid Latent Reasoning)， stable， we aim to extend this hybrid RL paradigm to open-ended agentic environments and explore scaling laws for longer-horizon latent planning. ， and geometrically rigorous latent policy optimization. Extensive experiments demonstrate that HyLaR significantly outperforms existing text-only and tool-augmented paradigms on fine-grained perception and reasoning benchmarks， exhibiting remarkable robustness to visual hallucinations. In future work，。
a novel framework designed to overcome early semantic collapse in MLLMs by seamlessly interleaving discrete textual logic with continuous visual working memory. To effectively optimize this hybrid discrete-continuous action space， In this work， DePO leverages von Mises-Fisher (vMF) spherical modeling and decoupled trust-region clipping to achieve exact。