@article{
chen2026cobalt,
title={{COBALT}: Contextual Bandit Learning with Offline Trajectories for Multi-Turn Code Generation},
author={Ziru Chen and Dongdong Chen and Ruinan Jin and Yingbin Liang and Yujia Xie and Huan Sun},
journal={Transactions on Machine Learning Research},
issn={2835-8856},
year={2026},
url={https://openreview.net/forum?id=7SwoUNzIxe},
note={}
}