SULLIVAN, Megan; HE, Boyang; EVANS, Patrick. Learning When to Reason: Gating LLM Inference for Cost-Efficient Serverless Function Scheduling at Scale. Academic Journal of Applied Sciences, [S. l.], v. 2, n. 1, p. 39–45, 2026. DOI: 10.54097/gwmv0761. Disponível em: https://asciences.org/index.php/ojs/article/view/65. Acesso em: 12 jun. 2026.