Liu, R.-B., Ma, C.-Z., Li, A., Sun, H., Li, X.-Y., & Li, M. (2026). ARBench: Algorithmic Reasoner or API Alchemist? Evaluating LLMs Beyond API Calls. Proceedings of the AAAI Conference on Artificial Intelligence, 40(38), 32105–32113. https://doi.org/10.1609/aaai.v40i38.40482