@article{multiturncodegenerationthroughsingle, title = {Multi-Turn Code Generation Through Single-Step Rewards}, author = {Arnav Kumar Jain and Gonzalo Gonzalez-Pumariega and Wayne Chen and Alexander M Rush and Wenting Zhao and Sanjiban Choudhury}, year = {2025}, eprint = {2502.20380}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2502.20380v1}, }