Ye, S., Liu, Q., Jiang, H., Zhang, Z., Yu, H., & Huang, Z. (2026). Themis: Automated Constraint-Aware Test Synthesis Framework for Code Reinforcement Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 40(40), 34432–34440. https://doi.org/10.1609/aaai.v40i40.40741