{"id":"2609.21378","title":"ArenaFlow: From Trajectory Ranking to Hierarchical Credit Propagation for Open-Ended Agent RL","url":"https://codeofpaper.com/paper/2609.21378","arxiv_url":"https://arxiv.org/abs/2609.21378","published":"2026-09-18","code":"none","best":null,"most_starred_community":null,"implementations":[],"possible_matches":0}