{"id":"2505.21668","title":"R1-Code-Interpreter: LLMs Reason with Code via Supervised and Multi-stage Reinforcement Learning","url":"https://codeofpaper.com/paper/2505.21668","arxiv_url":"https://arxiv.org/abs/2505.21668","published":"2025-05-27","code":"official","best":{"full_name":"yongchao98/R1-Code-Interpreter","url":"https://github.com/yongchao98/R1-Code-Interpreter","tier":"official","stars":49,"license":null,"framework":null,"language":"Python","last_commit":"2026-02-09T18:48:34"},"most_starred_community":null,"implementations":[{"full_name":"yongchao98/R1-Code-Interpreter","url":"https://github.com/yongchao98/R1-Code-Interpreter","tier":"official","stars":49,"license":null,"framework":null,"language":"Python","last_commit":"2026-02-09T18:48:34"}],"possible_matches":0}