ChemBOMAS: Accelerated Bayesian Optimization for Scientific Discovery in Chemistry with LLM-Enhanced Multi-Agent System

ICLR 2026 Conference Submission25214 Authors

Keywords: Bayesian Optimization, Data Augmentation, Knowledge-Driven Strategy, Large Language Model, AI4Science

TL;DR: ChemBOMAS is an LLM-enhanced multi-agent system that synergistically integrates data-driven pseudo-data generation with knowledge-driven search space partitioning to accelerate Bayesian optimization for scientific discovery by up to ten times.

Abstract: Bayesian optimization (BO) is a powerful tool for scientific discovery in chemistry, yet its efficiency is often hampered by the sparse experimental data and vast search space. Here, we introduce ChemBOMAS: a large language model (LLM)-enhanced multi-agent system that accelerates BO through synergistic data- and knowledge-driven strategies. Firstly, the data-driven strategy involves an 8B-scale LLM regressor fine-tuned on a mere 1% labeled samples for pseudo-data generation, robustly initializing the optimization process. Secondly, the knowledge-driven strategy employs a hybrid Retrieval-Augmented Generation approach to guide LLM in dividing the search space while mitigating LLM hallucinations. An Upper Confidence Bound algorithm then identifies high-potential subspaces within this established partition. Across the LLM-refined subspaces and supported by LLM-generated data, BO achieves the improvement of effectiveness and efficiency. Comprehensive evaluations across multiple scientific benchmarks demonstrate that ChemBOMAS set a new state-of-the-art, accelerating optimization efficiency by up to 5-fold compared to baseline methods.

Primary Area: applications to physical sciences (physics, chemistry, biology, etc.)

Submission Number: 25214