In-Context Black-Box Optimization with Unreliable Feedback

📰 ArXiv cs.AI

arXiv:2605.06187v1 Announce Type: cross Abstract: Black-box optimization in science and engineering often comes with side information: experts, simulators, pretrained predictors, or heuristics can suggest which candidates look promising. This information can accelerate search, but it can also be biased, input-dependent, or misleading. Feedback-aware BO methods typically handle one task at a time, limiting their ability to generalize over multiple sources of feedback. In-context optimizers addres

Published 9 May 2026

Full Article

Title: In-Context Black-Box Optimization with Unreliable Feedback

Abstract:
arXiv:2605.06187v1 Announce Type: cross Abstract: Black-box optimization in science and engineering often comes with side information: experts, simulators, pretrained predictors, or heuristics can suggest which candidates look promising. This information can accelerate search, but it can also be biased, input-dependent, or misleading. Feedback-aware BO methods typically handle one task at a time, limiting their ability to generalize over multiple sources of feedback. In-context optimizers addres
Read full paper → ← Back to Reads