mlsanityData to 7 Oct 2026

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

arXiv 2509.08736 ↗First posted 10 Sep 2025cs.LGcited by 3

On the map: LLM agents and tool use → Medical and scientific domain agents

Abstract (arXiv)

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.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use. Builds on 10 of its 34 references that are in the map. First posted on arXiv 10 Sep 2025.

Builds on

10 of 34 references.

References · 10

  1. 2019Scalable Global Optimization via Local Bayesian Optimizationcited by 359
  2. 2024Large Language Models to Enhance Bayesian Optimizationcited by 127
  3. 2020Sample-Efficient Optimization in the Latent Space of Deep Generative Models via Weighted Retrainingcited by 121
  4. 2020Learning Search Space Partition for Black-box Optimization using Monte Carlo Tree Searchcited by 87
  5. 2022Recent Advances in Bayesian Optimizationcited by 74
  6. 2024Analyzing and Reducing Catastrophic Forgetting in Parameter Efficient Tuningcited by 59
  7. 2019Sample-Efficient Neural Architecture Search by Learning Action Spacecited by 23
  8. 2024Bayesian Optimization with LLM-Based Acquisition Functions for Natural Language Preference Elicitationcited by 17
  9. 2024Monte Carlo Tree Search based Space Transfer for Black-box Optimizationcited by 7
  10. 2023High-Dimensional Bayesian Optimization via Semi-Supervised Learning with Optimized Unlabeled Data Samplingcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026AutoScientists: Self-Organizing Agent Teams for Long-Running Scientific Experimentationcited by 7
  2. 2026LABO: LLM-Accelerated Bayesian Optimization through Broad Exploration and Selective Experimentationcited by 4
  3. 2026Modular Multi-Task Learning for Chemical Reaction Predictioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025CheMatAgent: Enhancing LLMs for Chemistry and Materials Science through Tree-Search Based Tool Learning
  2. 2026M3OS: A Monte Carlo Graph Search-Orchestrated Multi-Agent LLM System for Evidence-Traced Molecular Optimization
  3. 2025LLMs for Bayesian Optimization in Scientific Domains: Are We There Yet?
  4. 2026Unleashing LLMs in Bayesian Optimization: Preference-Guided Framework for Scientific Discovery
  5. 2024A Review of Large Language Models and Autonomous Agents in Chemistry
  6. 2026LLM sequential decision making under uncertainty in biochemical domains
  7. 2025Collaborative Expert LLMs Guided Multi-Objective Molecular Optimization
  8. 2025MT-Mol:Multi Agent System with Tool-based Reasoning for Molecular Optimization