EP186: Harness engineering for near perfect small models

Title: Compiling Deterministic Structure into SLM HarnessesSource: http://arxiv.org/abs/2604.17450v1Summary:This paper introduces Semantic Gradient Descent (SGDe), a novel PAC-learning-based framework that compiles complex agentic workflows into optimized, deterministic execution plans for small language models. It establishes a new architectural primitive for agent design by leveraging frontier teacher models to iteratively refine student workflows via discrete semantic gradients.