{"id":"2609.21432","title":"GVPO++: Group Variance Policy Optimization for LLM Post-Training and On-Policy Distillation","url":"https://codeofpaper.com/paper/2609.21432","arxiv_url":"https://arxiv.org/abs/2609.21432","published":"2026-09-18","code":"none","best":null,"most_starred_community":null,"implementations":[],"possible_matches":0}