@article{reinforcinghumanbehaviorsimulationviaver, title = {Reinforcing Human Behavior Simulation via Verbal Feedback}, author = {Weiwei Sun and Xuhui Zhou and Jiarui Liu and Weihua Du and Haojia Sun and Yiqing Xie and Qianou Ma and Sihao Chen and Mengting Wan and Longqi Yang and Pei Zhou and Sherry Wu and Sean Welleck and Graham Neubig and Yiming Yang and Maarten Sap}, year = {2026}, eprint = {2605.20506}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2605.20506}, }