Unleashing LLMs in Bayesian Optimization: Preference-Guided Framework for Scientific Discovery

• URL: http://arxiv.org/abs/2605.17976v1
• Date: Mon, 18 May 2026 07:30:25 GMT
• Title: Unleashing LLMs in Bayesian Optimization: Preference-Guided Framework for Scientific Discovery
• Abstract summary: We propose LLM-Guided Bayesian Optimization (LGBO), a preference-guided BO framework that integrates semantic reasoning into the optimization loop.<n>In a new wet-lab optimization of Fe-Cr battery electrolytes, LGBO attains textbf90% of the best observed value within 6, whereas standard BO and existing LLM-augmented baselines require more than 10 iterations.
• Score: 32.51891966529322
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Scientific discovery is increasingly constrained by costly experiments and limited resources, underscoring the need for efficient optimization in AI for science. Bayesian Optimization (BO), though widely adopted for balancing exploration and exploitation, often exhibits slow cold-start performance and poor scalability in high-dimensional settings, limiting its applicability in real-world scientific problems. To overcome these challenges, we propose LLM-Guided Bayesian Optimization (LGBO), the first LLM preference-guided BO framework that continuously integrates the semantic reasoning of large language models (LLMs) into the optimization loop. Unlike prior works that use LLMs only for warm-start initialization or candidate generation, LGBO introduces a region-lifted preference mechanism that embeds LLM-driven preferences into every iteration, shifting the surrogate mean in a stable and controllable way. Theoretically, we prove that LGBO does not perform significantly worse than standard BO in the worst case, while achieving significantly faster convergence when preferences align with the objective. Empirically, LGBO consistently outperforms existing methods across diverse dry benchmarks in physics, chemistry, biology, and materials science. Most notably, in a new wet-lab optimization of Fe-Cr battery electrolytes, LGBO attains \textbf{90\% of the best observed value within 6 iterations}, whereas standard BO and existing LLM-augmented baselines require more than 10. Together, these results suggest that LGBO offers a promising direction for integrating LLMs into scientific optimization workflows.

Related papers

• FrontierOR: Benchmarking LLMs' Capacity for Efficient Algorithm Design in Large-Scale Optimization [61.43300970020897]
  Large language models (LLMs) are increasingly used for optimization modeling and solver-code generation.<n>Existing benchmarks are limited to small or simplified examples far below real-world scale and complexity.<n>We introduce FrontierOR, among the first benchmarks to evaluate LLM-based efficient algorithm design for realistic large-scale optimization problems.
  arXiv  Detail & Related papers  (2026-05-24T20:10:42Z)
• LABO: LLM-Accelerated Bayesian Optimization through Broad Exploration and Selective Experimentation [18.30782195527165]
  Large language models (LLMs) are knowledge-driven components in Bayesian optimization.<n>We propose a framework that combines LLM predictions with experimental observations within a single BO loop.<n>We show that LABO consistently outperforms existing methods under identical experimental budgets.
  arXiv  Detail & Related papers  (2026-05-21T06:42:47Z)
• BoLT: A Benchmark to Democratize Black-box Optimization Research for Expensive LLM Tasks [42.78958516953461]
  Black-box optimization methods offer a promising yet underexplored direction for principled, sample-efficient methods.<n>New methods are often only evaluated on synthetic test functions and small-scale datasets.<n>We introduce BoLT, the first LLM-centric benchmark that democratizes research for the BBO community.
  arXiv  Detail & Related papers  (2026-05-16T13:53:44Z)
• A Meta-Knowledge-Augmented LLM Framework for Hyperparameter Optimization in Time-Series Forecasting [0.0]
  We introduce LLM-AutoOpt, a hybrid HPO framework that combines BO with LLM-based contextual reasoning.<n>We show that LLM-AutoOpt achieves improved predictive performance and more interpretable optimization behavior compared to BO and LLM baselines without meta-knowledge.
  arXiv  Detail & Related papers  (2026-02-01T21:26:57Z)
• ChemBOMAS: Accelerated BO in Chemistry with LLM-Enhanced Multi-Agent System [72.63341091857959]
  We introduce ChemBOMAS: a large language model (LLM)-enhanced multi-agent system that accelerates Bayesian optimization.<n>Data-driven strategy involves an 8B-scale LLM regressor fine-tuned on a mere 1% labeled samples.<n>The knowledge-driven strategy employs a hybrid Retrieval-Augmented Generation approach to guide LLM in dividing the search space.<n>ChemBOMAS set a new state-of-the-art, accelerating optimization efficiency by up to 5-fold compared to baseline methods.
  arXiv  Detail & Related papers  (2025-09-10T16:24:08Z)
• Pre-trained knowledge elevates large language models beyond traditional chemical reaction optimizers [0.0]
  We demonstrate that pre-trained knowledge in large language models (LLMs) fundamentally changes this paradigm.<n>LLM-GO excels precisely where traditional methods struggle: complex categorical spaces requiring domain understanding rather than mathematical optimization.
  arXiv  Detail & Related papers  (2025-08-27T21:09:51Z)
• LLINBO: Trustworthy LLM-in-the-Loop Bayesian Optimization [5.844783557050259]
  Large Language Models (LLMs) have shown remarkable adaptability in low-data regimes.<n>We propose LLINBO: LLM-in-the-Loop BO, a hybrid framework for BO that combines LLMs with statistical surrogate experts.<n>We end the paper with a real-life proof-of-concept in the context of 3D printing.
  arXiv  Detail & Related papers  (2025-05-20T15:54:48Z)
• Less is More: Extreme Gradient Boost Rank-1 Adaption for Efficient Finetuning of LLMs [75.11449420928139]
  Fine-tuning Large Language Models (LLMs) has become a crucial technique for adapting pre-trained models to downstream tasks. Low-Rank Adaptation (LoRA) has emerged as a promising solution, but there exists a gap between the practical performance of low-rank adaptations and its theoretical optimum. We propose eXtreme Gradient Boosting LoRA, a novel framework that bridges this gap by leveraging the power of ensemble learning.
  arXiv  Detail & Related papers  (2024-10-25T17:07:13Z)
• Multi-Reference Preference Optimization for Large Language Models [56.84730239046117]
  We introduce a novel closed-form formulation for direct preference optimization using multiple reference models. The resulting algorithm, Multi-Reference Preference Optimization (MRPO), leverages broader prior knowledge from diverse reference models. Our experiments demonstrate that LLMs finetuned with MRPO generalize better in various preference data, regardless of data scarcity or abundance.
  arXiv  Detail & Related papers  (2024-05-26T00:29:04Z)
• Large Language Models to Enhance Bayesian Optimization [57.474613739645605]
  We present LLAMBO, a novel approach that integrates the capabilities of Large Language Models (LLM) within Bayesian optimization. At a high level, we frame the BO problem in natural language, enabling LLMs to iteratively propose and evaluate promising solutions conditioned on historical evaluations. Our findings illustrate that LLAMBO is effective at zero-shot warmstarting, and enhances surrogate modeling and candidate sampling, especially in the early stages of search when observations are sparse.
  arXiv  Detail & Related papers  (2024-02-06T11:44:06Z)
• Are Large Language Models Good Prompt Optimizers? [65.48910201816223]
  We conduct a study to uncover the actual mechanism of LLM-based Prompt Optimization. Our findings reveal that the LLMs struggle to identify the true causes of errors during reflection, tending to be biased by their own prior knowledge. We introduce a new "Automatic Behavior Optimization" paradigm, which directly optimize the target model's behavior in a more controllable manner.
  arXiv  Detail & Related papers  (2024-02-03T09:48:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.