{"id":"2610.27012","title":"Exploration via Activation-Space Steering for Reinforcement Learning with Verifiable Rewards","url":"https://codeofpaper.com/paper/2610.27012","arxiv_url":"https://arxiv.org/abs/2610.27012","published":"2026-10-19","code":"none","best":null,"most_starred_community":null,"implementations":[],"possible_matches":0}