{"id":"2601.22582","title":"MC-GRPO: Median-Centered Group Relative Policy Optimization for Small-Rollout Reinforcement Learning","url":"https://codeofpaper.com/paper/2601.22582","arxiv_url":"https://arxiv.org/abs/2601.22582","published":"2026-01-30","code":"none","best":null,"most_starred_community":null,"implementations":[],"possible_matches":0}