@article{3spostatescoresupervisedpolicyoptimizati, title = {3SPO: State-Score-Supervised Policy Optimization for LLM Agents}, author = {Yu Han and Kailing Li and Yang Jiao and Yulin Dai and Yuqian Fu and Linhai Zhuo and Tianwen Qian}, year = {2026}, eprint = {2606.09961}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.09961}, }