Geng, J., Wu, Z., Chen, K. S., Kim, S., Janssen, J., Wang, Z. Z., Kalita, B., Gao, R., Ho, A., Nelson, A. O., Isayev, O., Villaescusa-Navarro, F., Lai, C. Y., Chen, H., & Neubig, G. (2026). EurekaBench: Measuring Agentic Ability to Discover New Scientific Insights. https://omanscience.com/ar/articles/eurekabench-measuring-agentic-ability-to-discover-new-scientific-insights