@article{leanandmeandecoupledvaluepolicy, title = {Lean and Mean: Decoupled Value Policy Optimization with Global Value Guidance}, author = {Chenghua Huang and Lu Wang and Fangkai Yang and Pu Zhao and Zhixu Li and QIngwei Lin and Dongmei Zhang and Saravan Rajmohan and Qi Zhang}, year = {2025}, eprint = {2502.16944}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2502.16944v1}, }