YANG, Weibin; XIE, Liangru; CAI, Jieyun; YAN, Yuxiang; DAI, Hong-Ning; WANG, Hao. Talk2Code: A Multi-Turn Interaction Benchmark with Dual-Track Evaluation for Code Generation. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 40, n. 40, p. 34331–34339, 2026. DOI: 10.1609/aaai.v40i40.40730. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/40730. Acesso em: 15 may. 2026.