@inproceedings{chen2026qlpo,
  title = {QLPO: Quadrant-weighted Sampling for Length-aware Policy Optimization},
  author = {Chen, Siwei and Chen, Siqi and Miao, Xupeng and Cui, Bin},
  booktitle = {Conference on Language Modeling},
  year = {2026},
  eprint = {2607.21793},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2607.21793}
}