publications

AI Agents & Human–AI Decision Systems

1. Agents Last Exam

   2026

   Under review at NeurIPS 2026
2. DDO-RM: Distribution-Level Policy Improvement after Reward Learning

   Tiantian Zhang, Jierui Zuo, Michael Chen, and Wenping Wang

   arXiv preprint, 2026

   DOI arXiv PDF Code
3. Learning to Delegate with Costly Audit

   Jierui Zuo and Yingfei Wang

   2026

   Under review at NeurIPS 2026

   Bib

   @misc{zuo2026delegate,
     title = {Learning to Delegate with Costly Audit},
     author = {Zuo, Jierui and Wang, Yingfei},
     year = {2026},
     note = {Under review at NeurIPS 2026},
     selected = {true},
     bibtex_show = {true}
   }

Online Learning, Experimentation & Platform Design

1. Generator-Augmented Best-Arm Identification

   Jierui Zuo, Hanzhang Qin, and Ruihao Zhu

   2026

   Working paper

   Bib

   @misc{zuo2026learning,
     title = {Generator-Augmented Best-Arm Identification},
     author = {Zuo, Jierui and Qin, Hanzhang and Zhu, Ruihao},
     year = {2026},
     note = {Working paper},
     bibtex_show = {true}
   }

2. Experimental Design for Online Scheduling

   Jierui Zuo, Jinglong Zhao, and Zijie Zhou

   2026

   Working paper

   Bib

   @misc{zuo2026scheduling,
     title = {Experimental Design for Online Scheduling},
     author = {Zuo, Jierui and Zhao, Jinglong and Zhou, Zijie},
     year = {2026},
     note = {Working paper},
     bibtex_show = {true}
   }

3. On Pareto Optimality for Parametric Choice Bandits

   Jierui Zuo and Hanzhang Qin

   arXiv preprint, 2025

   arXiv Bib PDF

   @article{zuo2025pareto,
     title = {On Pareto Optimality for Parametric Choice Bandits},
     author = {Zuo, Jierui and Qin, Hanzhang},
     year = {2025},
     journal = {arXiv preprint},
     eprint = {2501.19277},
     archiveprefix = {arXiv},
     primaryclass = {cs.LG},
     url = {https://arxiv.org/abs/2501.19277},
     arxiv = {2501.19277},
     pdf = {https://arxiv.org/pdf/2501.19277},
     selected = {true},
     bibtex_show = {true}
   }