@article{monitoringreasoningmodelsformisbehavior, title = {Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation}, author = {Bowen Baker and Joost Huizinga and Leo Gao and Zehao Dou and Melody Y. Guan and Aleksander Madry and Wojciech Zaremba and Jakub Pachocki and David Farhi}, year = {2025}, eprint = {2503.11926}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2503.11926v1}, }