@article{hilbenchhumaninloopbenchmarkdoagentsknow, title = {HiL-Bench (Human-in-Loop Benchmark): Do Agents Know When to Ask for Help?}, author = {Tu Trinh and Mohamed Elfeki and Guangze Luo and Kelvin Luu and Nathan Hunt and Ernesto Hernandez and Nandan Marwaha and Yannis Yiming He and Charles Wang and Fernando Carabedo and Alessa Castillo and Bing Liu}, year = {2026}, eprint = {2604.09408}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2604.09408}, }