{"id":"2605.22643","title":"Boiling the Frog: A Multi-Turn Benchmark for Agentic Safety","url":"https://codeofpaper.com/paper/2605.22643","arxiv_url":"https://arxiv.org/abs/2605.22643","published":"2026-05-21","code":"none","best":null,"most_starred_community":null,"implementations":[],"possible_matches":0}