@article{learnhardproblemsduringrlwithreferencegu, title = {Learn Hard Problems During RL with Reference Guided Fine-tuning}, author = {Yangzhen Wu and Shanda Li and Zixin Wen and Xin Zhou and Ameet Talwalkar and Yiming Yang and Wenhao Huang and Tianle Cai}, year = {2026}, eprint = {2603.01223}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2603.01223}, }