@article{rlguideddataselectionforlanguagemodelfin, title = {RL-Guided Data Selection for Language Model Finetuning}, author = {Animesh Jha and Harshit Gupta and Ananjan Nandi}, year = {2025}, eprint = {2509.25850}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2509.25850}, }