{"id":"2610.13438","title":"Rollout-Time Intervention: Unlocking Agentic Reinforcement Learning Beyond Policy Limits","url":"https://codeofpaper.com/paper/2610.13438","arxiv_url":"https://arxiv.org/abs/2610.13438","published":"2026-10-09","code":"official","best":{"full_name":"Alibaba-NLP/qqr","url":"https://github.com/Alibaba-NLP/qqr","tier":"official","stars":269,"license":"Apache-2.0","framework":null,"language":"Python","last_commit":"2026-06-15T09:35:49"},"most_starred_community":null,"implementations":[{"full_name":"Alibaba-NLP/qqr","url":"https://github.com/Alibaba-NLP/qqr","tier":"official","stars":269,"license":"Apache-2.0","framework":null,"language":"Python","last_commit":"2026-06-15T09:35:49"}],"possible_matches":0}