@article{codeitselfimprovinglanguagemodelswith, title = {CodeIt: Self-Improving Language Models with Prioritized Hindsight Replay}, author = {Natasha Butt and Blazej Manczak and Auke Wiggers and Corrado Rainone and David W. Zhang and Michaƫl Defferrard and Taco Cohen}, year = {2024}, eprint = {2402.04858}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2402.04858v2}, }