WANG, Wenkai; GUO, Hongcan; LV, Zheqi; ZHANG, Shengyu. A Rolling Stone Gathers No Moss: Adaptive Policy Optimization for Stable Self-Evaluation in Large Multimodal Models. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 40, n. 40, p. 33666–33674, 2026. DOI: 10.1609/aaai.v40i40.40656. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/40656. Acesso em: 25 may. 2026.