AI RESEARCH
Embedding by Elicitation: Dynamic Representations for Bayesian Optimization of System Prompts
arXiv CS.AI
•
ArXi:2605.19093v1 Announce Type: new System prompts are a central control mechanism in modern AI systems, shaping behavior across conversations, tasks, and user populations. Yet they are difficult to tune when feedback is available only as aggregate metrics rather than per-example labels, failures, or critiques. We study this aggregate feedback setting as sample-constrained black-box optimization over discrete, variable-length text. We