{"id":"2604.25899","title":"Pythia: Exploiting Workflow Predictability for Efficient Agent-Native LLM Serving","url":"https://codeofpaper.com/paper/2604.25899","arxiv_url":"https://arxiv.org/abs/2604.25899","published":"2026-04-28","code":"none","best":null,"most_starred_community":null,"implementations":[],"possible_matches":0}