cs.LGNov 18, 2026

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

Authors: Dongjun Han, Mingyu Lee, Ikjin Lee

Organizations: Department of Mechanical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon 34141, Republic of Korea · Department of AX & Mechanical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon 34141, Republic of Korea · KAIST InnoCORE PRISM-AI Center, Korea Advanced Institute of Science and Technology (KAIST), Daejeon 34141, Republic of Korea

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 conventional MFBO by 61%. Knowledge quality, rather than the choice of LLM, determined whether the search was accelerated, as shown by a controlled study that varied the two independently. A knowledge-level ablation further quantified the contribution of each knowledge statement. These results show that LLM-interpreted expert knowledge can complement numerical data as an information source in MFBO.

Explore similar work

CardsList
  1. Bayesian Optimization with Rich Auxiliary Information via LLMs

    Sep 16, 2026Efe Mert Karagözlü, Rohit Sonker, Tejus Gupta +2Bayesian OptimizationLarge Language Model-Guided Optimization

  2. Evidence-Gated LLM Priors for Multi-Objective Bayesian Optimization

    Jun 1, 2026Jiangyu Chen, Ban YiBayesian OptimizationLarge Language Model-Guided Optimization

  3. LLINBO: Trustworthy LLM-in-the-Loop Bayesian Optimization

    May 20, 2025Chih-Yu Chang, Milad Azvar, Chinedum Okwudire +1Bayesian OptimizationBlack-Box Optimization