SUN, Yiliu; ZHAO, Zicheng; WEI, Yang; ZHANG, Yanfang; GONG, Chen. Well Begun, Half Done: Reinforcement Learning with Prefix Optimization for LLM Reasoning. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 40, n. 39, p. 33144–33152, 2026. DOI: 10.1609/aaai.v40i39.40598. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/40598. Acesso em: 16 may. 2026.