Prompt Optimization

Prompt optimization studies how to adapt instructions and other inputs so language and multimodal models perform better without necessarily changing their weights. Common approaches use textual feedback or gradients, evolutionary search, Bayesian optimization, bandits, and reinforcement learning, with validation examples guiding candidate selection. Work increasingly optimizes prompts alongside tool schemas, workflows, agent routing, and communication, across settings such as reasoning, retrieval, tool use, and image generation. Gains can depend heavily on the evaluation data and objective: prompts may overfit, break requirements they were not scored on, or trade accuracy against cost, readability, and robustness, making held-out testing and regression checks central challenges.