نسخة أولية وصول مفتوح
AdaEva: Accelerating LLM-Driven Algorithm Design with Adaptive Partial Evaluation
Large Language Models (LLMs) are increasingly used for automated algorithm design. However the computational cost of evaluating the generated algorithms can be excessive. We consider the common LLM-driven automated algorithm design (LLM4AD) setting in which a candidate algorithm is evaluated by aggregating its performa …