{"id":"2605.28295","title":"Diversifying RLVR Rollouts via First-Token Exploration","url":"https://codeofpaper.com/paper/2605.28295","arxiv_url":"https://arxiv.org/abs/2605.28295","published":"2026-05-27","code":"none","best":null,"most_starred_community":null,"implementations":[],"possible_matches":0}