@misc{instrumentaleval,
  title = {Evaluating the Paperclip Maximizer: Are RL-Based Language Models More Likely to Pursue Instrumental Goals?},
  url = {https://arxiv.org/abs/2502.12206},
  author = {Yufei He and Yuexin Li and Jiaying Wu and Yuan Sui and Yulin Chen and Bryan Hooi},
  year = {2025},
  date = {2025-02-16},
  version = {arXiv:2502.12206v1},
  note = {arXiv:2502.12206v1}
}

@misc{instrumentaleval-nuwa,
  title = {Evaluating the Paperclip Maximizer: Are RL-Based Language Models More Likely to Pursue Instrumental Goals? — NUWA research record},
  url = {https://whitzard.tech/nuwa/whitzard-index/work/instrumentaleval/},
  version = {2026-10-29.1},
  organization = {NUWA Frontier AI Safety Lab},
  howpublished = {Retained note edition: https://whitzard.tech/nuwa/whitzard-index/data/record-editions/2026-10-29.1--instrumentaleval.json},
  note = {NUWA research note. Source-reading scope and independent review status are stated on the record. Snapshot 2026-10-29.1. Retained note edition: https://whitzard.tech/nuwa/whitzard-index/data/record-editions/2026-10-29.1--instrumentaleval.json.}
}