Lù, X. H., Vattikonda, D., Hajimiri, S., Zadeh, F. P., BehnamGhader, P., Darwiche, G., Kazemnejad, A., Pal, C., Drouin, A., & Reddy, S. (2026). AgentHorizon: Evaluating Agentic Judges for Long-Horizon Computer-Use Tasks. https://omanscience.com/en/articles/agenthorizon-evaluating-agentic-judges-for-long-horizon-computer-use-tasks