@article{mlgymanewframeworkandbenchmarkfor, title = {MLGym: A New Framework and Benchmark for Advancing AI Research Agents}, author = {Deepak Nathani and Lovish Madaan and Nicholas Roberts and Nikolay Bashlykov and Ajay Menon and Vincent Moens and Amar Budhiraja and Despoina Magka and Vladislav Vorotilov and Gaurav Chaurasia and Dieuwke Hupkes and Ricardo Silveira Cabral and Tatiana Shavrina and Jakob Foerster and Yoram Bachrach and William Yang Wang and Roberta Raileanu}, year = {2025}, eprint = {2502.14499}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2502.14499v1}, }