{"id":"2609.15248","title":"Bandits with Probing: Optimal Regret and the Limits of Winner Feedback","url":"https://codeofpaper.com/paper/2609.15248","arxiv_url":"https://arxiv.org/abs/2609.15248","published":"2026-09-14","code":"none","best":null,"most_starred_community":null,"implementations":[],"possible_matches":0}