{"id":"2508.05170","title":"Posterior-GRPO: Rewarding Reasoning Processes in Code Generation","url":"https://codeofpaper.com/paper/2508.05170","arxiv_url":"https://arxiv.org/abs/2508.05170","published":"2025-08-07","code":"none","best":null,"most_starred_community":null,"implementations":[],"possible_matches":0}