@inproceedings{einarsson-2026-mazeeval,
    title = "{M}aze{E}val: A Benchmark for Testing Sequential Decision-Making in Language Models",
    author = "Einarsson, Hafsteinn",
    editor = "Piperidis, Stelios  and
      Bel, N{\'u}ria  and
      van den Heuvel, Henk  and
      Ide, Nancy  and
      Krek, Simon  and
      Toral, Antonio",
    booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
    month = may,
    year = "2026",
    address = "Palma de Mallorca, Spain",
    publisher = "ELRA Language Resource Association",
    url = "https://aclanthology.org/2026.lrec-1.27/",
    doi = "10.63317/4nm93hckcaf2",
    pages = "407--418"
}