The GRPO Tax is Smaller Than You Think: A Longitudinal Study of Capability Preservation During Reasoning Training
Published in Transactions on Machine Learning Research (TMLR), 2026
Recommended citation: M. Usama, "The GRPO Tax is Smaller Than You Think: A Longitudinal Study of Capability Preservation During Reasoning Training," Transactions on Machine Learning Research (TMLR), 2026.
Paper · Code
