cs.LGNov 18, 2026

HapBO: Harnessed αα-ππ Bayesian Optimization via Expert Natural Language Priors

Authors: Jean-Sébastien Giroux, Rose Guay Hottin, Marco Bonizzato

Organizations: Department of Electrical Engineering, Polytechnique Montréal, Montréal, Quebec, Canada. · MILA – Québec AI Institute, Montréal, Quebec, Canada. · Department of Neurosciences, Centre Interdisciplinaire de Recherche sur le Cerveau et l’apprentissage (CIRCA) and Centre d’Innovation Biomédicale, Université de Montréal, Montréal, Quebec, Canada.

Abstract

Bayesian Optimization (BO) can be substantially more sample-efficient when informed by prior knowledge about the problem. In practice, however, such knowledge is often available only in natural language, e.g., expert intuitions or documentation, rather than as the explicit probability distribution landscape that prior-guided BO methods may require. Leveraging it effectively demands both an expressive mapping from language to priors and robustness to information that may be misleading. We propose HapBO (Harnessed αα-ππ Bayesian Optimization), which elicits beliefs once from a human expert, a large language model (LLM), or both, and deterministically compiles a structured specification into a reusable belief function (π:X→[0,1]π: \mathcal{X} \to[0,1]), with a rich representation not restricted to a Gaussian family. Building on αα-ππBO, HapBO applies this belief function through a bounded positive multiplier on any nonnegative acquisition, preserving positive acquisition support and requiring no LLM calls during optimization. We prove that, for the Expected Improvement acquisition function (EI), HapBO preserves the standard simple-regret rate up to a bounded factor, even under adversarial beliefs. We evaluate HapBO on 40 HPOBench tasks, a synthetic suite in 6-15 dimensions and two real-world applications: cortical neurostimulation and constrained solar design. HapBO achieves the lowest aggregate HPOBench regret and strong real-world task performance, with zero in-loop token cost. In real-world applications it improves the optimization outcome even at budgets of 12-20 queries, and at a small fraction of the wall-clock and token costs of other LLM-based methods.

Figures & tables

Appendix figures & tables23 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Harnessing Large Language Models to Compile Task-Relevant Context into Bayesian Optimisation

    Sep 29, 2026Zhongwei Yu, Sourabh Roy, Bin Cao +3Bayesian OptimizationLarge Language Model-Guided Optimization

  2. Bayesian Optimization with Rich Auxiliary Information via LLMs

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

  3. Elicitation-Augmented Bayesian Optimization

    May 12, 2026Alvar Haltia, Ville Hyvönen, Samuel KaskiBayesian OptimizationHuman-in-the-Loop Evaluation