@inproceedings{battleday2026dig,
  abstract = {Discovery, formulating novel generalizations, is a central part of the scientific process. DiG-bench is a benchmark for scientific discovery through interaction and experimentation in controlled environments with unknown objectives. It contains 70 independent text-based games, each with unknown transformation rules that agents must uncover, across seven difficulty tiers. Twenty-one games are publicly released and the remaining games are held private for secure evaluation; every game was solved by at least one human on a first attempt.},
  author = {Ruairidh M. Battleday and Kai Sandbrink and Jimi Cullen-Drohan and Zihan Yan and Timothy Muller and Clare Maguire and Ales Kubicek and Fraser Greenlee-Scott and Sukrit Sumant and Tri Dao and Jürgen Schmidhuber and Michal Valko and Joshua Tenenbaum and Thomas L. Griffiths and Zeb Kurth-Nelson and James C.R. Whittington},
  booktitle = {2026},
  title = {{DiG-bench: Discovery in Games}},
  url = {https://misovalko.github.io/publications/battleday2026dig.pdf},
  year = {2026}
}