Large-Scale Online Learning for Generative List Recommendation in E-commerce: An Environment Policy Optimization Approach.

@inproceedings{wang-2026-largescale, author = {Yuan Wang and Zuoxi Yang and Ang Gao and Karl Gyllstrom and Jun Xu and Yashishi Ogawa and Zhiyu Li and Changshuo Zhang and Craig A. N. Soules and Ang Gao and Karl Gyllstrom and Alistair C. Veitch and Xiao Zhang and Changshuo Zhang and Craig A. N. Soules and Alistair C. Veitch and Xiao Zhang and Jun Xu and Yashishi Ogawa and Quan Lin}, editor = {Hannah Bast and Alistair Moffat and Falk Scholer and Marc Najork and Min Zhang and Hannah Bast and Marc Najork and Min Zhang}, title = {{Large-Scale Online Learning for Generative List Recommendation in E-commerce: An Environment Policy Optimization Approach}}, booktitle = {{Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2026, MelbourneVICAustralia, July 20-24, 2026}}, pages = {1823--1833}, publisher = {ACM}, year = {2026}, url = {https://doi.org/10.1145/3805712.3809577}, doi = {https://doi.org/10.1145/3805712.3809577} }