LLINBO：可信的 LLM-in-the-Loop 贝叶斯优化框架

View PDF HTML (experimental)

Abstract: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, LLMs lack explicit surrogate modeling and calibrated uncertainty, and their internal mechanisms remain opaque. This structural opacity can result in unnecessary experiments, which are costly in BO and may prevent the search from approaching the optimum. To address this, we propose LLINBO: LLM-in-the-Loop BO, a general framework that wraps existing LLM-based BO approaches, deciding when and how to act on their suggestions and when to revert to classical BO. We introduce three mechanisms for this interaction, each accompanied by a no-harm theoretical guarantee that ensures sublinear cumulative regret for common kernels while requiring no performance assumptions on the LLM. Beyond these theoretical guarantees, we show through simulation studies that LLINBO makes existing LLM-based BO more reliable while still exploiting the LLM's few-shot learning ability to outperform classical BO. We further demonstrate its practical use on a real-world, expensive 3D printing experiment. Code is available at this https URL.

Subjects:	Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
Cite as:	arXiv:2505.14756 [cs.LG]
	(or arXiv:2505.14756v3 [cs.LG] for this version)
	https://doi.org/10.48550/arXiv.2505.14756 arXiv-issued DOI via DataCite

Submission history

From: Chih-Yu Chang [view email]
[v1] Tue, 20 May 2025 15:54:48 UTC (6,905 KB)
[v2] Thu, 9 Oct 2025 17:09:12 UTC (6,924 KB)
[v3] Thu, 29 Oct 2026 23:20:28 UTC (10,063 KB)