@inproceedings{he-etal-2026-traceprobe,
    title = "{T}race{P}robe: An Execution-Based Benchmark for Diagnosing Safety Failures in {LLM} Agents",
    author = "He, Yuxiang  and
      Zhao, Jian  and
      Liu, Yufei  and
      Yuan, Yuchen  and
      Li, Xuelong",
    editor = "Lee, Hung-Yi  and
      Dev, Sunipa  and
      Li, Jessy  and
      Elliott, Desmond",
    booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.emnlp-main.1233/",
    pages = "28121--28140",
    ISBN = "979-8-89176-459-0"
}