My research lies at the interface between game theory, learning theory, and optimization. I aim to advance the design principles of intelligent systems towards strategic alignment — a paradigm centered on aligning the interests of all stakeholders to achieve mutually beneficial outcomes. Towards this end, I develop theories and techniques to 1) build incentive-aware AI agents with strategic intelligence and rationalizable behaviors; 2) understand the economics of intelligence for more sustainable AI ecosystems.
I am currently visiting the Data Science Institute at the University of Chicago, where my work focuses on evaluating and developing strong AI agents for open-domain forecasts, from the following major aspects:
Event Curation & Data Synthesis: sourcing and structuring forecasting events with high-quality predictive traces and rationales.
Web Retrieval & Evidence Integration: building adaptive web research pipelines that surface reliable, real-time information for future events.
Reinforcement Learning for Forecasting: designing rewards and training agents to improve predictive reasoning and uncertainty quantification.
Market Modeling & Strategy Optimization: analyzing prediction markets and developing robust betting strategies informed by AI forecasts.
If you share any related interests, let’s connect and chat!
@article{yang2025llm,title={LLM-as-a-Prophet: Understanding Predictive Intelligence with Prophet Arena},author={Yang, Qingchuan and Mahns, Simon and Li, Sida and Gu, Anri and Wu, Jibang and Xu, Haifeng},journal={arXiv preprint arXiv:2510.17638},year={2025},}
A Truth Serum for Eliciting Self-Evaluations in Scientific Reviews
@article{wu2023isotonic,title={A Truth Serum for Eliciting Self-Evaluations in Scientific Reviews},author={Wu, Jibang and Xu, Haifeng and Guo, Yifan and Su, Weijie},status={R&R at Operations Research},}
Contractual Reinforcement Learning: Pulling Arms with Invisible Hands
@article{wu2024contractual,title={Contractual Reinforcement Learning: Pulling Arms with Invisible Hands},author={Wu, Jibang and Chen, Siyu and Wang, Mengdi and Wang, Huazheng and Xu, Haifeng},journal={arXiv preprint arXiv:2407.01458},year={2024},}
Grounded Persuasive Language Generation for Automated Marketing
Jibang Wu*, Chenghao Yang*, Simon Mahns, Chaoqi Wang, Hao Zhu, Fei Fang, and Haifeng Xu
@article{wu2024grounded,title={Grounded Persuasive Language Generation for Automated Marketing},author={Wu*, Jibang and Yang*, Chenghao and Mahns, Simon and Wang, Chaoqi and Zhu, Hao and Fang, Fei and Xu, Haifeng},journal={preprint},year={2024},}
Auctioning with Strategically Reticent Bidders
Jibang Wu, Ashwinkumar Badanidiyuru, and Haifeng Xu
@inproceedings{wu2021auctioning,title={Auctioning with Strategically Reticent Bidders},author={Wu, Jibang and Badanidiyuru, Ashwinkumar and Xu, Haifeng},booktitle={Proceedings of the 20th Conference on Web and Internet Economics},year={2024},series={WINE '24},}
Generalized Principal-Agency: Contracts, Information, Games and Beyond
(α-β) Jiarui Gan, Minbiao Han, Jibang Wu, and Haifeng Xu
@inproceedings{gan2022optimal,title={Generalized Principal-Agency: Contracts, Information, Games and Beyond},author={Gan, Jiarui and Han, Minbiao and Wu, Jibang and Xu, Haifeng},booktitle={Proceedings of the 20th Conference on Web and Internet Economics},year={2024},series={WINE '24},}
Robust Stackelberg Equilibria
(α-β) Jiarui Gan, Minbiao Han, Jibang Wu, and Haifeng Xu
EC 2023
Full Version Published at Mathematical Programming
@inproceedings{10.1145/3580507.3597680,author={Gan, Jiarui and Han, Minbiao and Wu, Jibang and Xu, Haifeng},title={Robust Stackelberg Equilibria},year={2023},isbn={9798400701047},publisher={Association for Computing Machinery},address={New York, NY, USA},url={https://doi.org/10.1145/3580507.3597680},booktitle={Proceedings of the 24th ACM Conference on Economics and Computation},pages={735},numpages={1},location={London, United Kingdom},series={EC '23},status={Full Version Published at Mathematical Programming},}
Learning to Incentivize Information Acquisition: Proper Scoring Rules Meet Principal-Agent Model
@article{chen2023learning,title={Learning to Incentivize Information Acquisition: Proper Scoring Rules Meet Principal-Agent Model},author={Chen, Siyu and Wu, Jibang and Wu, Yifan and Yang, Zhuoran},journal={arXiv preprint arXiv:2303.08613},year={2023},}
Inverse Game Theory for Stackelberg Games: the Blessing of Bounded Rationality
@article{wu2022inverse,title={Inverse Game Theory for Stackelberg Games: the Blessing of Bounded Rationality},author={Wu, Jibang and Shen, Weiran and Fang, Fei and Xu, Haifeng},journal={Advances in Neural Information Processing Systems},volume={35},pages={32186--32198},year={2022},}
Sequential Information Design: Markov Persuasion Process and Its Efficient Reinforcement Learning
Jibang Wu, Zixuan Zhang, Zhe Feng, Zhaoran Wang, Zhuoran Yang, Michael I. Jordan, and Haifeng Xu
@inproceedings{10.1145/3490486.3538313,author={Wu, Jibang and Zhang, Zixuan and Feng, Zhe and Wang, Zhaoran and Yang, Zhuoran and Jordan, Michael I. and Xu, Haifeng},title={Sequential Information Design: Markov Persuasion Process and Its Efficient Reinforcement Learning},year={2022},isbn={9781450391504},publisher={Association for Computing Machinery},address={New York, NY, USA},url={https://doi.org/10.1145/3490486.3538313},booktitle={Proceedings of the 23rd ACM Conference on Economics and Computation},pages={471–472},numpages={2},location={Boulder, CO, USA},series={EC '22},}
Multi-Agent Learning for Iterative Dominance Elimination: Formal Barriers and New Algorithms
@inproceedings{wu2021multi,title={Multi-Agent Learning for Iterative Dominance Elimination: Formal Barriers and New Algorithms},author={Wu, Jibang and Xu, Haifeng and Yao, Fan},booktitle={Proceedings of Thirty Fifth Conference on Learning Theory},pages={543--543},year={2022},editor={Loh, Po-Ling and Raginsky, Maxim},volume={178},series={Proceedings of Machine Learning Research},month={02--05 Jul},publisher={PMLR},status={R&R at Journal of Machine Learning Research},}
Least square calibration for peer reviews
Sijun Tan*, Jibang Wu*, Xiaohui Bei, and Haifeng Xu
@article{tan2021least,title={Least square calibration for peer reviews},author={Tan*, Sijun and Wu*, Jibang and Bei, Xiaohui and Xu, Haifeng},journal={Advances in Neural Information Processing Systems},volume={34},pages={27069--27080},year={2021},}
@inproceedings{cai2021category,title={Category-aware collaborative sequential recommendation},author={Cai, Renqin and Wu, Jibang and San, Aidan and Wang, Chong and Wang, Hongning},booktitle={Proceedings of the 44th international ACM SIGIR conference on research and development in information retrieval},pages={388--397},year={2021},}
Déjà vu: A contextualized temporal attention mechanism for sequential recommendation
@inproceedings{wu2020deja,title={D{\'e}j{\`a} vu: A contextualized temporal attention mechanism for sequential recommendation},author={Wu, Jibang and Cai, Renqin and Wang, Hongning},booktitle={Proceedings of The Web Conference 2020},pages={2199--2209},year={2020},}
Prophet Arena, a live benchmark for predictive intelligence, is publicly launched. Check out our technical report, blog post, news coverages. 
I organized a tutorial on Principal-Agent Decision-Making Processes at WINE’24 conference.
I gave a guest lecture on Game Theory and Principal-Agent Modeling in Smart Mobility for IE 691: Advanced Topics in Industrial Engineering. 
My thesis received the Stigler Center Ph.D. Dissertation Award. Check out the news coverage!