@misc{maldaner_arxiv2026, title={SentinelBench: A Benchmark for Long-Running Monitoring Agents}, author={Matheus Kunzler Maldaner and Adam Fourney and Amanda Swearngin and Hussein Mozannar and Gagan Bansal and Maya Murad and Rafah Hosn and Saleema Amershi}, year={2026}, eprint={2606.05342}, archivePrefix={arXiv}, primaryClass={cs.AI}, url={https://arxiv.org/abs/2606.05342}, }