@article{llmscancovertlysandbagoncapabilityevalua, title = {LLMs Can Covertly Sandbag on Capability Evaluations Against Chain-of-Thought Monitoring}, author = {Chloe Li and Mary Phuong and Noah Y. Siegel}, year = {2025}, eprint = {2508.00943}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2508.00943}, }