@article{evaluatingthepaperclipmaximizerarerl,
  title = {Evaluating the Paperclip Maximizer: Are RL-Based Language Models More Likely to Pursue Instrumental Goals?},
  author = {Yufei He and Yuexin Li and Jiaying Wu and Yuan Sui and Yulin Chen and Bryan Hooi},
  year = {2025},
  eprint = {2502.12206},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2502.12206v1},
}