LLM Evaluation Using Prompt Learning

As more agents get deployed, a question emerges: can reinforcement learning control systems be built only in prompts? After all, reinforcement learning is all about using real-world feedback to optimize toward a goal, traditionally by adjusting model weights. But prompts themselves are the primary interface for guiding large language models. ​Prompt learning (PL) is a new approach and algorithm developed by Arize AI. Unlike traditional optimization methods that rely on numerical scores, prompt learning uses natural language feedback to iteratively improve prompts. In this session, AI Engineer Priyan Jindal will cover prompt learning best practices and practical tips for implementing it — including via the Arize AX prompt learning SDK.