@article{spectralpolicyoptimizationcoloringyour, title = {Spectral Policy Optimization: Coloring your Incorrect Reasoning in GRPO}, author = {Peter Chen and Xiaopeng Li and Ziniu Li and Xi Chen and Tianyi Lin}, year = {2025}, eprint = {2505.11595}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2505.11595v1}, }