{"id":"2412.18319","title":"Mulberry: Empowering MLLM with o1-like Reasoning and Reflection via Collective Monte Carlo Tree Search","url":"https://codeofpaper.com/paper/2412.18319","arxiv_url":"https://arxiv.org/abs/2412.18319","published":"2024-12-24","code":"official","best":{"full_name":"HJYao00/Mulberry","url":"https://github.com/HJYao00/Mulberry","tier":"official","stars":1244,"license":null,"framework":null,"language":"Python","last_commit":"2026-01-16T08:02:56"},"most_starred_community":null,"implementations":[{"full_name":"HJYao00/Mulberry","url":"https://github.com/HJYao00/Mulberry","tier":"official","stars":1244,"license":null,"framework":null,"language":"Python","last_commit":"2026-01-16T08:02:56"}],"possible_matches":1}