@misc{mle-bench,
  title = {MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering},
  url = {https://arxiv.org/abs/2410.07095},
  author = {Jun Shern Chan and Neil Chowdhury and Oliver Jaffe and James Aung and Dane Sherburn and Evan Mays and Giulio Starace and Kevin Liu and Leon Maksin and Tejal Patwardhan and Lilian Weng and Aleksander Mądry},
  year = {2024},
  date = {2024-10-09},
  version = {arXiv:2410.07095v6},
  note = {arXiv:2410.07095v6}
}

@misc{mle-bench-nuwa,
  title = {MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering — NUWA research record},
  url = {https://whitzard.tech/en/nuwa/whitzard-index/work/mle-bench/},
  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--mle-bench.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--mle-bench.json.}
}