← All episodes
EPISODE 186

Harness engineering for near perfect small models

Learning GenAI via SOTA Papers · May 15, 2026 · 25 min

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.

Listen on: Spotify · Apple Podcasts · Amazon Music · YouTube

Follow the show: YouTube · Medium · X · LinkedIn · Bluesky · Threads · Instagram · TikTok · Facebook · Telegram