{"id":"2605.03862","title":"Correct Is Not Enough: Training Reasoning Planners with Executor-Grounded Rewards","url":"https://codeofpaper.com/paper/2605.03862","arxiv_url":"https://arxiv.org/abs/2605.03862","published":"2026-05-05","code":"none","best":null,"most_starred_community":null,"implementations":[],"possible_matches":0}