@article{smallrlcontrollerlargelanguagemodelrlgui,
  title = {Small RL Controller, Large Language Model: RL-Guided Adaptive Sampling for Test-Time Scaling},
  author = {Runpeng Dai and Tong Zheng and Rui Liu and Chengsong Huang and Hongtu Zhu},
  year = {2026},
  eprint = {2606.03102},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.03102},
}