{"id":"2510.18814","title":"Online SFT for LLM Reasoning: Surprising Effectiveness of Self-Tuning without Rewards","url":"https://codeofpaper.com/paper/2510.18814","arxiv_url":"https://arxiv.org/abs/2510.18814","published":"2025-10-21","code":"none","best":null,"most_starred_community":null,"implementations":[],"possible_matches":0}