Saved in:
Bibliographic Details
Main Authors: Chang, Chih-Yu, Azvar, Milad, Okwudire, Chinedum, Kontar, Raed Al
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.14756
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911200067977216
author Chang, Chih-Yu
Azvar, Milad
Okwudire, Chinedum
Kontar, Raed Al
author_facet Chang, Chih-Yu
Azvar, Milad
Okwudire, Chinedum
Kontar, Raed Al
contents Bayesian optimization (BO) is a sequential decision-making tool widely used for optimizing expensive black-box functions. Recently, Large Language Models (LLMs) have shown remarkable adaptability in low-data regimes, making them promising tools for black-box optimization by leveraging contextual knowledge to propose high-quality query points. However, relying solely on LLMs as optimization agents introduces risks due to their lack of explicit surrogate modeling and calibrated uncertainty, as well as their inherently opaque internal mechanisms. This structural opacity makes it difficult to characterize or control the exploration-exploitation trade-off, ultimately undermining theoretical tractability and reliability. To address this, we propose LLINBO: LLM-in-the-Loop BO, a hybrid framework for BO that combines LLMs with statistical surrogate experts (e.g., Gaussian Processes (GP)). The core philosophy is to leverage contextual reasoning strengths of LLMs for early exploration, while relying on principled statistical models to guide efficient exploitation. Specifically, we introduce three mechanisms that enable this collaboration and establish their theoretical guarantees. We end the paper with a real-life proof-of-concept in the context of 3D printing. The code to reproduce the results can be found at https://github.com/UMDataScienceLab/LLM-in-the-Loop-BO.
format Preprint
id arxiv_https___arxiv_org_abs_2505_14756
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LLINBO: Trustworthy LLM-in-the-Loop Bayesian Optimization
Chang, Chih-Yu
Azvar, Milad
Okwudire, Chinedum
Kontar, Raed Al
Machine Learning
Artificial Intelligence
Bayesian optimization (BO) is a sequential decision-making tool widely used for optimizing expensive black-box functions. Recently, Large Language Models (LLMs) have shown remarkable adaptability in low-data regimes, making them promising tools for black-box optimization by leveraging contextual knowledge to propose high-quality query points. However, relying solely on LLMs as optimization agents introduces risks due to their lack of explicit surrogate modeling and calibrated uncertainty, as well as their inherently opaque internal mechanisms. This structural opacity makes it difficult to characterize or control the exploration-exploitation trade-off, ultimately undermining theoretical tractability and reliability. To address this, we propose LLINBO: LLM-in-the-Loop BO, a hybrid framework for BO that combines LLMs with statistical surrogate experts (e.g., Gaussian Processes (GP)). The core philosophy is to leverage contextual reasoning strengths of LLMs for early exploration, while relying on principled statistical models to guide efficient exploitation. Specifically, we introduce three mechanisms that enable this collaboration and establish their theoretical guarantees. We end the paper with a real-life proof-of-concept in the context of 3D printing. The code to reproduce the results can be found at https://github.com/UMDataScienceLab/LLM-in-the-Loop-BO.
title LLINBO: Trustworthy LLM-in-the-Loop Bayesian Optimization
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2505.14756