@article{massdpomultinegativeactivesampleselectio, title = {MASS-DPO: Multi-negative Active Sample Selection for Direct Policy Optimization}, author = {Rohan Surana and Xintong Li and Sheldon Yu and Yiran Jenny Shen and Chuhan Wang and Tong Yu and Prithviraj Ammanabrolu and Jingbo Shang and Julian McAuley and Junda Wu}, year = {2026}, eprint = {2605.10784}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2605.10784}, }