ChemBOMAS: Accelerated BO in Chemistry with LLM-Enhanced Multi-Agent System

2025-09-10

AI Summary

Chemical Bayesian optimization (BO) suffers from low search efficiency due to sparse experimental data and complex reaction mechanisms. To address this, we propose an LLM-augmented multi-agent collaborative optimization framework. Our method leverages large language models (LLMs) for knowledge-guided decomposition of the reaction space, enabling synergistic coarse-grained pathway planning and fine-grained parameter optimization; additionally, it generates high-fidelity pseudo-data grounded in chemical mechanistic principles to alleviate data scarcity. By integrating knowledge-driven reasoning with data-driven modeling, the framework significantly outperforms conventional BO across multiple benchmark tasks. Wet-lab validation demonstrates a 96% success rate in achieving target reaction outcomes—over sixfold higher than the domain expert baseline (15%)—establishing a scalable new paradigm for high-throughput chemical optimization.

Technology Category

• Search and Optimization: Learning to Search
• Intelligent Robots: Learning & Optimization for ROB
• Reasoning under Uncertainty: Stochastic Optimization

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

Abstract

The efficiency of Bayesian optimization (BO) in chemistry is often hindered by sparse experimental data and complex reaction mechanisms. To overcome these limitations, we introduce ChemBOMAS, a new framework named LLM-Enhanced Multi-Agent System for accelerating BO in chemistry. ChemBOMAS's optimization process is enhanced by LLMs and synergistically employs two strategies: knowledge-driven coarse-grained optimization and data-driven fine-grained optimization. First, in the knowledge-driven coarse-grained optimization stage, LLMs intelligently decompose the vast search space by reasoning over existing chemical knowledge to identify promising candidate regions. Subsequently, in the data-driven fine-grained optimization stage, LLMs enhance the BO process within these candidate regions by generating pseudo-data points, thereby improving data utilization efficiency and accelerating convergence. Benchmark evaluations** further confirm that ChemBOMAS significantly enhances optimization effectiveness and efficiency compared to various BO algorithms. Importantly, the practical utility of ChemBOMAS was validated through wet-lab experiments conducted under pharmaceutical industry protocols, targeting conditional optimization for a previously unreported and challenging chemical reaction. In the wet experiment, ChemBOMAS achieved an optimal objective value of 96%. This was substantially higher than the 15% achieved by domain experts. This real-world success, together with strong performance on benchmark evaluations, highlights ChemBOMAS as a powerful tool to accelerate chemical discovery.

Problem

• Accelerating Bayesian optimization for chemical reactions
• Overcoming sparse data and complex reaction mechanisms
• Enhancing optimization with LLM-driven multi-agent strategies

Innovation

• LLM-Enhanced Multi-Agent System for chemical optimization
• Knowledge-driven coarse-grained optimization using chemical reasoning
• Data-driven fine-grained optimization with pseudo-data generation