@inproceedings{kanda-etal-2026-workflowperturb, title = "{W}orkflow{P}erturb: Calibrated Stress Tests for Evaluating Multi-Agent Workflow Metrics", author = "Kanda, Madhav and Agarwal, Sharad and Fonseca, Rodrigo and Kumbhare, Alok Gautam and Las-Casas, Pedro", editor = "Atanasova, Pepa and Haffari, Gholamreza and Wang, Minghan", booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track", month = oct, year = "2026", address = "Budapest, Hungary", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2026.emnlp-industry.25/", pages = "394--411", ISBN = "979-8-89176-460-6" }