{"id":"2602.01058","title":"Good SFT Optimizes for SFT, Better SFT Prepares for Reinforcement Learning","url":"https://codeofpaper.com/paper/2602.01058","arxiv_url":"https://arxiv.org/abs/2602.01058","published":"2026-02-01","code":"none","best":null,"most_starred_community":null,"implementations":[],"possible_matches":0}