Skip to contentDEEKOYA AI CoursesFLAT 20% OFFEnroll Now
Deekoya AI

LLM-Assisted Multi-Fidelity Bayesian Optimization: Fusing Expert Knowledge with Numerical Data

Dongjun Han, Mingyu Lee, Ikjin Lee · 18 Nov 2026 · arXiv

Abstract

Multi-fidelity Bayesian optimization (MFBO) reduces engineering design cost by combining inexpensive low-fidelity (LF) models with a few accurate high-fidelity (HF) evaluations and sequentially selecting designs to evaluate. However, when HF data are scarce, the LF-HF discrepancy is difficult to learn from numerical data alone, especially when physics omitted in the LF model makes it design-dependent. Yet even without sufficient data, domain experts often know which physics the LF model omits and under which conditions its effect grows. Existing multi-fidelity (MF) models cannot use such qualitative knowledge directly, but large language models (LLMs) can interpret it and compare designs accordingly. The proposed LLM-Assisted MFBO adds a knowledge basis to the conventional MF model: from an expert description of the omitted physics, an LLM judges which of two designs requires the larger signed residual correction, and a pairwise Gaussian process converts these judgments into the basis. HF data calibrate its contribution and sign, so the knowledge is not trusted blindly. On a lithium-ion battery design problem, the proposed method reduced the regret area under the curve of conventio

cs.LGcs.AIcs.CE

Comments

No comments yet. Share your own experience below.

Visitor posts are moderated before they appear and are the opinion of their authors, not DEEKOYA AI. Names are not verified. See our privacy policy.